All books | Heidelberg AI Curriculum

Progress is saved in this browser only.

18 books

Chat & assistants1

T02-L04A Self-Hosted Assistant Your Team Can Use SafelyA one-page assistant record (model and where prompts go, who can reach it, how accounts are approved, who administers it, allowed data classes, backups) plus Open WebUI running on one machine with a non-admin test account; it passes when the test account can chat but can't open the Admin Panel, sign-up is off, and a colleague answers three paste questions correctly from the record alone.Integrator20 min read

Prompting & context1

T03-L04Release Prompt Changes Through Review, Tests and a Way BackA prompt repository with one released change: the pull request with its automatic test run and approval, the release tag recorded in production outputs, and a rehearsed rollback. It passes when a colleague rolls production back to the previous tag from the README alone in under ten minutes, and IT has confirmed the access list in writing.Integrator22 min read

Your documents & knowledge1

T04-L04Connect an Assistant to Real Documents Without Widening Anyone's AccessA permission test record for one connected source: the access model and why, the sign-offs, two ordinary test accounts, a marker document and the results for the authorised account, the outside account and a removed member. It passes when the outside account surfaces no marker, title, snippet or citation anywhere, the shared control works for both, and removal took effect within the stated window.Integrator20 min read

Automation1

T05-L04Make an Automation Safe to Fail Before It Touches Real SystemsOne n8n workflow that writes to a real system, with a failure test sheet and a takeover page; it passes when all five injected failures (double run, revoked login, empty input, timeout on the irreversible step, three failures in a row) end where the sheet says, IT and the data owner have signed, and a deputy takes over by hand from the page alone.Integrator22 min read

Build apps1

T06-L04Put Your Team App on the Organisation's Own Database, and Prove You Can Restore ItA restore record and a role test sheet for a team app whose data lives in a Supabase your organisation runs; it passes when the restored copy, built from the off-server backup into an empty database, gives the same answers to every line of the role test sheet, no admin key appears in the app, and IT and the data owner have signed.Integrator22 min read

Agents1

T07-L04Connect an Agent to a Real Mailbox Without Handing It the KeysA connection record for one agent working on a real mailbox or business system: the access granted and the denials proved, the gate rules, a before-and-after run of at least three planted-instruction tests, the sign-offs, and a tested switch-off. It passes when every planted instruction ends as a draft for a person or a refusal, and IT has signed.Integrator22 min read

Write code1

T08-L04Use OpenCode Desktop on Your Organisation's Real RepositoriesOne merged pull request in a real team repository, made with OpenCode, plus a one-page repository record. It passes when main rejects a direct push, a second person approved the pull request against the spec, the secret scan and tests ran before the push, and the record names the account, its access and the undo.Integrator26 min read

Create media1

T09-L04Transcribe Recordings That Must Stay in the BuildingA signed one-page data route plus a working local transcription setup; it passes when the test clips pass the check with the local model, fit and speed are measured on your own hardware, the job account is shown to be unable to read outside its folder, one approved real recording has a reviewed transcript, and a colleague has run the stop-and-delete procedure from the run sheet.Integrator23 min read

Data & analysis1

T10-L04Connect Your Analysis to a Live System, and Stop Bad Data Before It Reaches AnyoneA scheduled pipeline reading a live source through a read-only account; it passes when a deliberately corrupted copy of the source makes the run stop with a clear message and leaves the last accepted output unchanged, a write attempt with the pipeline's account is refused, the data owner and IT have signed the field list, and a colleague can rerun a stopped week from the run sheet.Integrator20 min read

Run your own AI1

T11-L04Put Your Team's Assistant on a Server Colleagues Can ReachA server record for your team's assistant, plus a second-device test: it passes when the HTTPS address works from a colleague's computer, the Open WebUI and model ports don't answer from there, a restore from last night's backup has worked on another machine, and IT (plus the data protection officer if chats hold personal data) has signed the record.Integrator23 min read

Security, privacy & governance1

T12-L04Lock Down a Self-Hosted AI Service Before Real Data Goes InA dated five-step audit of a self-hosted AI service: every finding with its fix, who fixed it and the retest result, plus one denied-access test and one restore test. It passes when every step has a result, no finding is open without a named person and a date, and IT has signed.Integrator20 min read

Adoption & enablement1

T13-L04Roll Out an AI Assistant to a Whole Department, With Access, Cost and Consent Settled FirstA rollout plan and the results of its first wave; it passes when every seat is tied to a named role and task, the cost includes people's time, the oversharing check and its fixes are recorded, the DPO and the works or staff council have signed, access is removable by one group change, and after wave one the plan shows accepted outcomes, unused seats and every objection with its answer.Integrator19 min read

Connect your tools1

T14-L04Build a Read-Only Connector for a System Your Assistant Can't Reach YetA working read-only connector with its README and a test sheet of six cases; it passes when all six give the expected result, a write attempt through the same key is refused by the system itself, a colleague's run shows only what their own access allows, and the system's administrator has agreed in writing.Integrator18 min read

AI in research1

T15-L04Set Up AI for a Whole Research GroupA one-page group AI-use policy plus a data map (each data source, its class, the tools allowed, who has access), reviewed and signed by the PI with a review date; it passes when every data source the group uses appears in the map and a new member can answer three paste questions from the policy alone.Integrator20 min read

Choose tools1

T16-L04Replace a Tool Without Losing Your WorkA migration record for one team (inventory with a decision per item, re-test results in the new tool, cutover plan with rollback trigger, list of revoked keys and closed accounts, sign-offs); it passes when a pilot user completes the team's three most important jobs in the new tool without the old one, the rollback was tried on copies, and every credential the old tool used is accounted for.Integrator17 min read

Structure & understand1

T17-L04Run a Pilot with Real Users and Real DataA pilot plan and a results note for a real pilot, which pass when the criteria and decision rule are dated before the start, data permissions are confirmed in writing, every criterion (including harm) has a measured result, and the go, change or stop decision follows the rule and is signed by the person who decides.Integrator18 min read

Share & review code1

T19-L04Check Every Change Automatically, Release Versions and Tell the LabA repository where a required automatic check runs on every pull request, one pull request was blocked by it and fixed, and publishing release v1.0 posted a message in the chat using the secret address.Integrator18 min read

AI harnesses1

T20-L04Set Up a Harness So a Mistake Stays Small: Container, Rules, Keys and NetworkThe four promises with their layers, the two probe rows (before and after), and the practice task result in the final set-up. Passes when the after-row shows internet and writing outside blocked, no promise depends on a harness rule alone, the key expires and is limited to one model, and a colleague can rerun the probe.Integrator20 min read