--- title: "SAP AI Workshop: AI for ABAP Teams in One Day" description: "SAP AI workshop on your exported ABAP code and Jira data, no connection into SAP. 12 people for 2,400 EUR or the whole IT team of 50 for 3,900 EUR." url: "https://www.engineeringleaders.io/academy/ai-for-sap-teams" lang: "en" image: "https://www.engineeringleaders.io/academy/_astro/workshop-16.eonU-KWG.webp" --- In-house, for SAP teams: 1 prep day + 1 workshop day # SAP AI Workshop for ABAP Teams Smart use of AI in SAP teams. One real ticket done by 5 pm. - A full SDLC guide for SAP, enriched by AI - Ten AI skills tailored to your SAP team - 71% faster cycle in an 18-person SAP team [Request a 30-minute call](mailto:academy@engineeringleaders.io?subject=Book%20an%20in-house%20cohort%2C%20SAP%20AI%20Workshop%20for%20ABAP%20Teams)[Take the free AI SDLC for SAP test](https://www.engineeringleaders.io/academy/ai-sdlc-for-sap) 2,400/3,900 EUR excl. VAT Group average under 8 out of 10: everyone gets the full amount back. The SAP AI Workshop is a one-day, in-house workshop for SAP development teams of up to 12 people, run on your own ABAP code exported to files and on your own backlog, with no connection from AI into your SAP system. It is built on what cut implementation cycle time by 71% in an 18-person SAP team. Every participant leaves with a setup where Claude Code reads the exported SAP code without copy-paste, and one real ticket finished with AI. For the whole IT team there is a 50-person format in two tracks. ![Participants at an Engineering Leaders Academy workshop working on their laptops while Marian Kamenistak walks the room through results on the screen, the hands-on format of the SAP AI workshop](https://www.engineeringleaders.io/academy/_astro/workshop-16.eonU-KWG_m8wQ6.webp) Trusted by ![Rohlik](https://www.engineeringleaders.io/academy/_astro/rohlik.DjmtOPhX_1ucs3n.webp)![Microsoft](https://www.engineeringleaders.io/academy/_astro/microsoft.CsBl2bmK_ZbDFT4.webp)![Kiwi.com](https://www.engineeringleaders.io/academy/_astro/kiwi-com.B7F1kSvW_21Kv9O.webp)![FTMO](https://www.engineeringleaders.io/academy/_astro/ftmo.vGjlobvw_C2AJY.webp) Not for - Teams that want a talk about AI. The day has fewer than ten slides and runs on your exported code. - Teams that expect AI to write into SAP on the day. Code goes back into SAP through a person, and transports stay with a person. Who it is for - SAP development teams of up to 12 people (ABAP, reporting, BW or HANA) who want SAP AI training on their own code and backlog. - Teams whose developers paste ABAP into a chat, get textbook answers back, and conclude that AI does not work for SAP. - Companies where SAP and IT infrastructure or helpdesk should start together: up to 50 people in two tracks. ## The prep day Marian prepares the SAP specifics together with your SAP lead. Without this day the workshop stays generic and the first hour goes on installs. Many on-premise SAP IT teams allow no AI connection into SAP, and the workshop does not need one. Where your IT approves it, we also test SAP’s ADT MCP server as an optional second route. 1. ### Kickoff call, 60 minutes With you and your SAP lead: the landscape (ECC, S/4HANA, BW, HANA), Jira or Azure DevOps, which AI licences people have, what may leave your network, and whether your IT allows any AI connection into SAP. 2. ### 4 to 6 real tickets Picked from your backlog. For each one we write down how long that kind of ticket takes today. That is the baseline. 3. ### Your code in files The packages we will work on, exported through abapGit or as Z-code and DDIC structures in a repo, plus a Jira or Azure DevOps export. We check that Claude Code reads them on a developer laptop. Whatever will not work, we know before the day. 4. ### House rules for AI A CLAUDE.md with your conventions: Z/Y naming, Clean ABAP, authority checks, banned patterns. 5. ### Participant checklist Sent a week before: licences, access, installs. ### What we need from you - A Claude licence with Claude Code for each participant (Pro is enough, training switched off on private accounts). - Approval to export the packages. - A 6-month Jira or Azure DevOps export with its structure. - Your SAP lead on the kickoff call, with 4 to 6 tickets. - A room with a projector and one laptop per pair. The program ## The workshop day: 9:00 to 17:00, in pairs, on your own tickets 1. 9:00 to 9:30 ### Same ticket, twice. One of your tickets solved by pasting into a chat, then again with the exported package and your house rules loaded. The difference shows on your own code. 2. 9:30 to 10:30 ### One setup for everyone. IDE with Claude Code over the exported code, house rules in CLAUDE.md, the Jira or Azure DevOps export at hand. The same setup on every laptop. Where your IT approves it, SAP’s ADT MCP server in Eclipse as an optional second route. 3. 10:45 to 12:00 ### Specification. AI reads the exported code and sharpens the spec for the new feature, then scores it against the 8 of 10 gate. Stories, tasks and test cases ready for Jira or Azure DevOps. 4. 12:45 to 14:15 ### Build and fix. Pairs take their own ticket from spec to code. A bug fixed from an ST22 dump or an SQL trace. ABAP Unit tests for Z-code that never had any. The code goes back into SAP by a person; nothing on the day writes into your system. 5. 14:30 to 15:30 ### Review and docs. A code review agent checking against Clean ABAP and ATC results. A documentation agent writing the documentation for Confluence. The team keeps both. 6. 15:30 to 16:15 ### Limits and rules. What AI sees in your exports and what it does not. The team writes its own rules: what never goes into AI, what an export may contain (no production data), how AI code gets reviewed. Transports stay with a person. 7. 16:15 to 17:00 ### Results. Three or four pairs show what worked and what did not. Each person picks one practice for four weeks and we agree the metric. 8. Whole IT team format, track A1 ### AI in ABAP development. For the ABAP developers. One shared tooling setup for all of them: IDE with Claude Code, shared DDIC context and conventions, reusable skills. Real old Z-code taken to modern ABAP with ABAP Unit tests and a Clean ABAP check. Then one real spec all the way through: spec check, design with two options, code with tests, a person approving between steps. Outcome: a faster development cycle and predefined tooling across the SAP developers. 9. Whole IT team format, track A2 ### Efficiency metrics on Jira. For SAP consultants, helpdesk and infrastructure, on a 6-month Jira export. Scores spec quality against the 8 of 10 gate, evaluates the last sprints against plan, builds a sprint morning brief, and traces one helpdesk incident from its log to severity, probable root cause and, in the IDE, the related objects in the exported Z-code and a proposed fix. A person decides. Outcome: 3 agreed metrics for productivity and quality of sprint delivery. ![Engaged audience during a Q&A at an Engineering Leaders meetup](https://www.engineeringleaders.io/academy/_astro/meetup-18.DX1W40oI_1ljyLw.webp) ## From where you are, to where you walk out. Before A developer pastes a piece of ABAP into a chat. The model sees one snippet, none of your Z-tables, DDIC structures, includes or naming rules, and writes textbook ABAP that does not fit your system. After Claude Code reads the whole exported package and your house rules, and the same model writes code that compiles against your system. No AI connects into SAP for that. Before Each developer pastes snippets into their own chat window, in their own way. After One shared setup on every laptop, a CLAUDE.md with your house rules, and two reusable agents for code review and documentation. Before Specs reach the team unscored. In the 18-person team the average spec scored 3.3 out of 10 at the start. After A spec scorer on your Jira or Azure DevOps export. Below 8 out of 10, a spec does not go to the team. Before Developers buy AI themselves and run company code through private accounts the company cannot see or control. After Team rules for AI, written by the people who follow them, and a licence option the company owns. Before There is no number to say whether AI moved anything. After A baseline measured on the prep day, and the cycle time of that ticket type compared with it four weeks later. ## What you walk out able to do. - A full SDLC guide for your SAP team, enriched by AI: what AI does and what a person approves at every step, from Jira ticket to transport. - Your AI skills, defined and tailored: the ten SAP skills from spec-grill to bugfix adapted to your conventions, ready as a Claude Code plugin and GitHub Copilot prompts. - One real ticket from your backlog, done with AI by 5 pm. - One shared setup: Claude Code over your exported code, the same on every laptop. No more pasting, and no connection into SAP. - CLAUDE.md with your house rules for SAP work, shared across the team and every new licence. - Two reusable agents: one for code review, one for documentation. - A spec scorer on your Jira or Azure DevOps export: the 8 of 10 gate, with a live connection to Jira or Confluence only where your IT allows it. - Team rules for AI, written by the people who follow them. - A baseline and a metric for the next four weeks. ![Marian Kamenistak leading a workshop at a screen with notes on the whiteboard, the hands-on format the SAP team day uses](https://www.engineeringleaders.io/academy/_astro/workshop-whiteboard.BOTNUCfW_ZJh8O7.webp) ![Engineering leaders discussing a case in a training room](https://www.engineeringleaders.io/academy/_astro/workshop-03.CuYEwHQP_Z1pwo45.webp) ![Engineering leaders networking between sessions](https://www.engineeringleaders.io/academy/_astro/meetup-20.CZ-hrmfx_3bdmh.webp) ![Participants comparing notes during an Academy workshop](https://www.engineeringleaders.io/academy/_astro/workshop-13.CmYPWKKk_ZFvrTt.webp) Format ## Format and price. - One prep day with your SAP lead, then one workshop day with your team on site, 9:00 to 17:00. - Up to 12 people in six pairs, each pair on its own ticket. Twelve is as many as one trainer can support when everyone works on their own code. 13 to 14 people with an optional assistant. - Every participant scores the day at the end. If the team average is under 8 out of 10, the workshop is free: you get the full amount back. - A Claude Code workshop with fewer than ten slides. It runs on code exported to files and on a Jira or Azure DevOps export; nothing on the day writes into SAP. - Whole IT team: up to 50 people, SAP and IT infrastructure or helpdesk together, run by Marian and an assistant. A 75-minute opening for everyone (a live build of a small app, and the numbers from the 18-person team), then two tracks. Before that day: a 60-minute call on your tooling and data, then half a day of data preparation (the export cleaned, names replaced by initials). Standard: up to 12 people 2,400 EUR excl. VAT 1 prep day + 1 workshop day. Optional assistant for 13 to 14 people: +1,000 EUR. Whole IT team: up to 50 people 3,900 EUR excl. VAT 1 prep day + 1 workshop day in two tracks, one lecturer each, run with an assistant. Optional review after four weeks +600 EUR excl. VAT Half a day on the metric, four weeks after the workshop. The 8/10 rule When you pay Before the workshop, by invoice Who scores it Every participant, at the end of the workshop day Team average under 8 out of 10 The workshop is free: you get the full amount back, no questions [Request a 30-minute call](mailto:academy@engineeringleaders.io?subject=Book%20an%20in-house%20cohort%2C%20SAP%20AI%20Workshop%20for%20ABAP%20Teams) Both prices follow one rate card: 1,200 EUR per day for the lead trainer, the assistant on top. Travel billed at cost. Paid before the workshop. Invoiced by Engineering Leaders Academy: Czech VAT at 21% for Czech clients, reverse charge for EU businesses with a VAT ID. Faculty ## Who teaches you You learn from people who did the job. Our lecturers have built multiple unicorn companies and helped organizations scale from startup to scale-up to established corporate. No academic theories, no empty certificates. ![Marian Kamenistak, Engineering Leaders Community](https://www.engineeringleaders.io/academy/_astro/lecturer-marian.BcY-YzfF_1gRKxE.webp) ### Marian Kamenistak Engineering Leaders Community Time to Value, Release cycle, Software talent, Team autonomy, Scalability ![Petr Glaser, BleedingDev](https://www.engineeringleaders.io/academy/_astro/lecturer-petr-glaser.cGIDjUZ5_ZHlpSx.webp) ### Petr Glaser BleedingDev AI Agents, AI in Engineering ![A training environment full of engineering managers at work](https://www.engineeringleaders.io/academy/_astro/web-2025-11-13-072.DS2Dlv8D_1xhOrd.webp) ![An engineering leader presenting to peers in a workshop](https://www.engineeringleaders.io/academy/_astro/workshop-10.CTCOy70n_ZfdSvx.webp) Hard to copy ## The parts a competitor cannot copy in a quarter. 01 ### Your code, not a demo. The day runs on your exported packages and on 4 to 6 tickets from your own backlog, picked on the prep day. People work in pairs on their own tickets. 02 ### No connection into SAP. Many on-premise SAP IT teams allow no AI connection into SAP, and the workshop does not need one: abapGit or a repo export is enough. SAP’s ADT MCP server stays an optional second route where your IT approves it. If neither route reads your code reliably on the prep day, GitHub Copilot in Eclipse is the fallback. 03 ### A hypothesis we can prove wrong. Targets sit well below what the 18-person team reached: 30% instead of 71%. If cycle time moves less than 10% by week 4, we look at which step broke: the setup (the agent cannot read your code), the context (house rules missing) or the review (seniors rewrite what AI produced). 04 ### The tools stay with the team. The skills, the spec evaluator and the installation guide are one plugin. The ten base skills are open source on GitHub (sap-ai-skills); on the workshop they get your team’s own rules. > “SAP is not the problem and neither is the model. The model gets one snippet.” Proof ## Already working in an 18-person SAP team. - In an SAP team Marian works with (18 people, ABAP and reporting, client under NDA), the median cycle time in the implementation phase fell from 19 days to about 5.5 in five weeks: -71%. - Resolution time on SLA tickets fell from 2.72 days to about 1.4 in the same five weeks: -49%. - Specs before code: SAP-related skills read the codebase to find the contracts and the relevant bugs before anyone implements. A spec rated below 8 out of 10 does not go to the team; the average spec scored 3.3 at the start. - An incident agent took over categorisation that used to depend on one person’s knowledge. It was built in 3 hours; the person still handles the 20% of tickets where its confidence is low, and the logs land in the Jira issue. - AI buddies: every developer pairs with someone more advanced in AI, with one shared set of skills and an installation guide. The 71% cannot be split between the spec gate, the skills, the pairing and the incident agent; they started in the same weeks. The team’s own answer is the spec gate. - [How the spec gate works, with the scoring rubric →](https://www.marian.coach/blog/spec-driven-development-sap/) - [Free test: AI SDLC for SAP →](https://www.engineeringleaders.io/academy/ai-sdlc-for-sap) Sample workshop deck ## See the slides of an SAP workshop day. The deck for a workshop day with an SAP team on NetWeaver 7.40, 73 slides: a seven-step install guide, a five-minute write test, how to split into four groups and work as a mob, one slide on how each AI skill works before the group runs it, the exact prompts step by step, and how the team writes its SDLC guide and onboarding guide at the end. [Open the sample deck →](https://www.engineeringleaders.io/sap-ai-adoption-slides/) [![Title slide of the sample SAP workshop deck: Your SAP lifecycle, with AI. Four groups, ten AI skills, your own ABAP code on DEV, next to a drawing of three stacked layers: Claude Code, MCP server, SAP DEV](https://www.engineeringleaders.io/academy/samples/sap-workshop-deck/cover.webp)](https://www.engineeringleaders.io/sap-ai-adoption-slides/) Questions ## What buyers ask before they book. Can GitHub Copilot or Claude write ABAP code? Yes. In an independent benchmark of 180 ABAP tasks, Claude Opus 4.6 solved 84% of them after compiler feedback rounds. The weak point is context: a pasted snippet carries none of your Z-tables, DDIC structures or naming rules, so the model writes generic ABAP. Giving it the exported package and your house rules fixes that, with no connection into SAP. Does the workshop need the SAP ADT MCP server or any connection into SAP? No. The workshop runs on code exported to files, through abapGit or as packages exported to a repo, and on a Jira export. Many on-premise SAP IT teams allow no AI connection into SAP, and none is needed. Where your IT approves it, SAP’s ADT MCP server is an optional second route: SAP’s own connector that lets AI agents search, check, test and activate ABAP objects from Eclipse. It shipped in 2026, most of its tools cost nothing to run, and SAP states support down to release 7.31 SP04, on-premise and cloud, ECC included. From ADT 3.62 it also reads and edits source code; on ADT 3.60 and 3.61 a community extension adds reading. Why does ChatGPT give bad ABAP answers when I paste a snippet? Because the snippet is all it sees. Your Z-tables, DDIC structures, includes and conventions stay inside the SAP system, so the model guesses and writes textbook ABAP. The workshop replaces pasting with the whole package, exported through abapGit to files and loaded together with your house rules. Where your IT approves it, SAP’s ADT MCP server can read the code live instead. Can the whole IT team join, not only the SAP developers? Yes. The larger format takes up to 50 people, SAP and IT infrastructure or helpdesk together, run by Marian and an assistant. A 75-minute opening for everyone, then two tracks: AI in ABAP development on exported Z-code, and efficiency metrics on a 6-month Jira export. The team leaves with one shared tooling setup for its ABAP developers and 3 agreed metrics. 3,900 EUR excluding VAT, travel at cost. Can AI read SAP BW and HANA objects? Partly. BW objects such as aDSOs, transformations and DTPs have no text source and no public API, so AI reads only the ABAP and AMDP routines inside them. HANA calculation views and HDI artifacts are text and XML files in Business Application Studio or VS Code, and AI reads those well. HANA Studio is not recommended: SAP stopped developing it in 2017. SAP GUI has no AI assistant for developers; AI-assisted development runs in Eclipse with ADT, VS Code or BAS. Do we need Claude Enterprise for this workshop? No. The workshop runs on the licences your team already has, and Claude Pro is enough because it includes Claude Code. For company code we recommend Claude Team, from 20 USD per user per month (claude.com/pricing, October 2026): the company owns the accounts and chats are not used for training by default. Is it safe to use private AI accounts on company SAP code? Not by default. On private Claude accounts (Free, Pro, Max), chats are used for model training since 28 August 2025 unless the user switches it off, and are then kept for up to five years. The company cannot see that setting or enforce it, and when someone leaves, the history with your code stays on their private account. ST22 dumps and table extracts can also contain personal data. The minimum, today: switch training off on every private account and keep production data and dumps with personal data out of AI. When does the workshop pay back? An example for a team of 12: going from 5 to 3.5 days saves 1.5 days per ticket. If each developer closes one such ticket every three weeks, that is half a day a week per developer, or 6 days a week for the team. At an internal cost of 400 EUR a developer day (an assumption, your number will differ), that is 2,400 EUR a week, so the workshop pays back in its first week. On the prep day your real baseline replaces the example and we agree the targets together. Who runs it? Marian Kamenistak. He is not an ABAP developer, and the workshop does not pretend otherwise. The SAP specifics come from your SAP lead on the prep day; Marian brings the AI setup, the agents and the way to make a team use them. ## Where to go next. More from the Academy - [AI1: Get on AI track](https://www.engineeringleaders.io/academy/ai-augmented) - [AI2: Spread the AI](https://www.engineeringleaders.io/academy/ai-managers) - [AI3: AI Masters](https://www.engineeringleaders.io/academy/ai-masters) - [AI4: Executive AI](https://www.engineeringleaders.io/academy/executive-ai) - [All ELC Academy courses](https://www.engineeringleaders.io/academy/) In the ELC community - [1:1 mentoring for engineering leaders](https://www.engineeringleaders.io/mentor/) - [Upcoming ELC meetups](https://www.engineeringleaders.io/events/) - [Free ELC membership](https://www.engineeringleaders.io/partner/membership/free/) ## SAP AI Workshop for ABAP Teams Tell us your SAP landscape, how many people would join (12 developers or the whole IT team) and which AI licences they use today. You get the fit and a date proposal on the call. [Request a 30-minute call](mailto:academy@engineeringleaders.io?subject=Book%20an%20in-house%20cohort%2C%20SAP%20AI%20Workshop%20for%20ABAP%20Teams) Ready for the full operating rebuild? [The AI-Native Engineering Manager →](https://www.engineeringleaders.io/academy/ai-native-engineering-manager) ## Structured data ```json {"@context":"https://schema.org","@type":"Organization","@id":"https://www.engineeringleaders.io/academy#org","name":"Engineering Leaders Academy","url":"https://www.engineeringleaders.io/academy","parentOrganization":{"@type":"Organization","name":"Engineering Leaders Community","url":"https://www.engineeringleaders.io"},"founder":{"@id":"https://www.engineeringleaders.io/academy#marian"},"areaServed":"Central Europe","aggregateRating":{"@type":"AggregateRating","ratingValue":"9.3","bestRating":"10","ratingCount":54}} {"@context":"https://schema.org","@type":"Person","@id":"https://www.engineeringleaders.io/academy#marian","name":"Marian Kamenistak","jobTitle":"Founder & Lead Facilitator","description":"Founder of the 3,500+ member Engineering Leaders community. Scaled Mews engineering 8 to 80 teams through Series C. Databricks, Manta (acquired by IBM). 3,400+ mentoring sessions with 300+ leaders in 17+ countries.","image":"https://www.engineeringleaders.io/academy/_astro/marian-portrait-enhanced.DpsglcYj.webp","worksFor":{"@id":"https://www.engineeringleaders.io/academy#org"},"alumniOf":{"@type":"CollegeOrUniversity","name":"Charles University, Prague"},"knowsAbout":["Engineering leadership","Engineering management","Fractional CTO","Scaling engineering teams","Technical leadership coaching"],"sameAs":["https://www.linkedin.com/in/mariankamenistak","https://github.com/marian-kamenistak","https://www.crunchbase.com/person/marian-kamenistak","https://www.wikidata.org/wiki/Q140488098","https://www.youtube.com/@engineeringleaders"]} {"@context":"https://schema.org","@type":"WebSite","name":"Engineering Leaders Academy","url":"https://www.engineeringleaders.io/academy"} {"@context":"https://schema.org","@type":"WebPage","name":"SAP AI Workshop: AI for ABAP Teams in One Day","url":"https://www.engineeringleaders.io/academy/ai-for-sap-teams","description":"SAP AI workshop on your exported ABAP code and Jira data, no connection into SAP. 12 people for 2,400 EUR or the whole IT team of 50 for 3,900 EUR.","dateModified":"2026-11-12","isPartOf":{"@type":"WebSite","name":"Engineering Leaders Academy","url":"https://www.engineeringleaders.io/academy"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Engineering Leaders Academy","item":"https://www.engineeringleaders.io/academy/"},{"@type":"ListItem","position":2,"name":"SAP AI Workshop: AI for ABAP Teams in One Day","item":"https://www.engineeringleaders.io/academy/ai-for-sap-teams"}]} {"@context":"https://schema.org","@type":"Course","name":"SAP AI Workshop for ABAP Teams","description":"SAP AI workshop on your exported ABAP code and Jira data, no connection into SAP. 12 people for 2,400 EUR or the whole IT team of 50 for 3,900 EUR.","url":"https://www.engineeringleaders.io/academy/ai-for-sap-teams","inLanguage":"en","educationalLevel":"In-house","teaches":["A full SDLC guide for your SAP team, enriched by AI: what AI does and what a person approves at every step, from Jira ticket to transport.","Your AI skills, defined and tailored: the ten SAP skills from spec-grill to bugfix adapted to your conventions, ready as a Claude Code plugin and GitHub Copilot prompts.","One real ticket from your backlog, done with AI by 5 pm.","One shared setup: Claude Code over your exported code, the same on every laptop. No more pasting, and no connection into SAP.","CLAUDE.md with your house rules for SAP work, shared across the team and every new licence.","Two reusable agents: one for code review, one for documentation.","A spec scorer on your Jira or Azure DevOps export: the 8 of 10 gate, with a live connection to Jira or Confluence only where your IT allows it.","Team rules for AI, written by the people who follow them.","A baseline and a metric for the next four weeks."],"dateModified":"2026-11-12","image":"https://www.engineeringleaders.io/academy/_astro/workshop-16.eonU-KWG.webp","provider":{"@id":"https://www.engineeringleaders.io/academy#org"},"instructor":[{"@id":"https://www.engineeringleaders.io/academy#marian"},{"@type":"Person","name":"Petr Glaser","worksFor":{"@type":"Organization","name":"BleedingDev"},"image":"https://www.engineeringleaders.io/academy/_astro/lecturer-petr-glaser.cGIDjUZ5.jpg","knowsAbout":["AI Agents","AI in Engineering"],"sameAs":["https://www.linkedin.com/in/bleedingdev"]}],"offers":[{"@type":"Offer","name":"Standard: up to 12 people","category":"Paid","price":"2400","priceCurrency":"EUR","availability":"https://schema.org/InStock","priceValidUntil":"2027-11-14","url":"https://www.engineeringleaders.io/academy/ai-for-sap-teams"},{"@type":"Offer","name":"Whole IT team: up to 50 people","category":"Paid","price":"3900","priceCurrency":"EUR","availability":"https://schema.org/InStock","priceValidUntil":"2027-11-14","url":"https://www.engineeringleaders.io/academy/ai-for-sap-teams"},{"@type":"Offer","name":"Optional review after four weeks","category":"Paid","price":"600","priceCurrency":"EUR","availability":"https://schema.org/InStock","priceValidUntil":"2027-11-14","url":"https://www.engineeringleaders.io/academy/ai-for-sap-teams"}],"hasCourseInstance":{"@type":"CourseInstance","courseMode":"onsite","courseWorkload":"1 day","location":{"@type":"Place","name":"Central Europe (Prague, Brno, Bratislava and Krakow)"}}} {"@context":"https://schema.org","@type":"FAQPage","mainEntity":[{"@type":"Question","name":"Can GitHub Copilot or Claude write ABAP code?","acceptedAnswer":{"@type":"Answer","text":"Yes. In an independent benchmark of 180 ABAP tasks, Claude Opus 4.6 solved 84% of them after compiler feedback rounds. The weak point is context: a pasted snippet carries none of your Z-tables, DDIC structures or naming rules, so the model writes generic ABAP. Giving it the exported package and your house rules fixes that, with no connection into SAP."}},{"@type":"Question","name":"Does the workshop need the SAP ADT MCP server or any connection into SAP?","acceptedAnswer":{"@type":"Answer","text":"No. The workshop runs on code exported to files, through abapGit or as packages exported to a repo, and on a Jira export. Many on-premise SAP IT teams allow no AI connection into SAP, and none is needed. Where your IT approves it, SAP’s ADT MCP server is an optional second route: SAP’s own connector that lets AI agents search, check, test and activate ABAP objects from Eclipse. It shipped in 2026, most of its tools cost nothing to run, and SAP states support down to release 7.31 SP04, on-premise and cloud, ECC included. From ADT 3.62 it also reads and edits source code; on ADT 3.60 and 3.61 a community extension adds reading."}},{"@type":"Question","name":"Why does ChatGPT give bad ABAP answers when I paste a snippet?","acceptedAnswer":{"@type":"Answer","text":"Because the snippet is all it sees. Your Z-tables, DDIC structures, includes and conventions stay inside the SAP system, so the model guesses and writes textbook ABAP. The workshop replaces pasting with the whole package, exported through abapGit to files and loaded together with your house rules. Where your IT approves it, SAP’s ADT MCP server can read the code live instead."}},{"@type":"Question","name":"Can the whole IT team join, not only the SAP developers?","acceptedAnswer":{"@type":"Answer","text":"Yes. The larger format takes up to 50 people, SAP and IT infrastructure or helpdesk together, run by Marian and an assistant. A 75-minute opening for everyone, then two tracks: AI in ABAP development on exported Z-code, and efficiency metrics on a 6-month Jira export. The team leaves with one shared tooling setup for its ABAP developers and 3 agreed metrics. 3,900 EUR excluding VAT, travel at cost."}},{"@type":"Question","name":"Can AI read SAP BW and HANA objects?","acceptedAnswer":{"@type":"Answer","text":"Partly. BW objects such as aDSOs, transformations and DTPs have no text source and no public API, so AI reads only the ABAP and AMDP routines inside them. HANA calculation views and HDI artifacts are text and XML files in Business Application Studio or VS Code, and AI reads those well. HANA Studio is not recommended: SAP stopped developing it in 2017. SAP GUI has no AI assistant for developers; AI-assisted development runs in Eclipse with ADT, VS Code or BAS."}},{"@type":"Question","name":"Do we need Claude Enterprise for this workshop?","acceptedAnswer":{"@type":"Answer","text":"No. The workshop runs on the licences your team already has, and Claude Pro is enough because it includes Claude Code. For company code we recommend Claude Team, from 20 USD per user per month (claude.com/pricing, October 2026): the company owns the accounts and chats are not used for training by default."}},{"@type":"Question","name":"Is it safe to use private AI accounts on company SAP code?","acceptedAnswer":{"@type":"Answer","text":"Not by default. On private Claude accounts (Free, Pro, Max), chats are used for model training since 28 August 2025 unless the user switches it off, and are then kept for up to five years. The company cannot see that setting or enforce it, and when someone leaves, the history with your code stays on their private account. ST22 dumps and table extracts can also contain personal data. The minimum, today: switch training off on every private account and keep production data and dumps with personal data out of AI."}},{"@type":"Question","name":"When does the workshop pay back?","acceptedAnswer":{"@type":"Answer","text":"An example for a team of 12: going from 5 to 3.5 days saves 1.5 days per ticket. If each developer closes one such ticket every three weeks, that is half a day a week per developer, or 6 days a week for the team. At an internal cost of 400 EUR a developer day (an assumption, your number will differ), that is 2,400 EUR a week, so the workshop pays back in its first week. On the prep day your real baseline replaces the example and we agree the targets together."}},{"@type":"Question","name":"Who runs it?","acceptedAnswer":{"@type":"Answer","text":"Marian Kamenistak. He is not an ABAP developer, and the workshop does not pretend otherwise. The SAP specifics come from your SAP lead on the prep day; Marian brings the AI setup, the agents and the way to make a team use them."}}]} ```