By role

How each discipline works in the agentic PDLC (product, programme, architecture, engineering, forward-deployed, QA, DevOps, the sponsor and the executive): what changes, what is theirs, and what is not.

9 lessonsabout 58 minutesYour job, phase by phase

1. 1The agentic PDLC for product managers: what changes MondayWhat an AI product manager does in the agentic PDLC: measure the pain, decide if it is AI at all, set autonomy per action, derive the bar, report two numbers.6 min · Beginner
2. 2Agentic PDLC for program managers: boards, bolts, reportingHow a program or delivery manager runs agentic AI delivery: the board, the cadence, the decision log, the review queue, gate conditions and two numbers.7 min · Beginner
3. 3Agentic PDLC for solution architects: authority and topologyWhat a solution architect decides in agentic AI: which steps may be probabilistic, how many agents, the authority budget, where caps live, and the records.7 min · Intermediate
4. 4The agentic PDLC for software engineers: build with agentsHow software engineers work in the agentic PDLC: a context file, story files, exact code first, gated tools, a harness that decides merges, and a bolt a day.6 min · Beginner
5. 5AI-DLC and AIDD for forward-deployed engineers: field guideHow a forward-deployed engineer runs AI-DLC and AIDD at a customer: measure their pain, have their risk owner sign the limits, build in their stack, hand over.7 min · Intermediate
6. 6The agentic PDLC for QA: how to test probabilistic softwareHow QA works in the agentic PDLC: the proof each step owes, golden sets by slice, lower bounds instead of scores, injection suites, shadow runs and drift.6 min · Intermediate
7. 7The agentic PDLC for DevOps and platform teamsWhat DevOps and platform teams own in agentic AI: the landing zone, one model gateway, pinned versions, the harness as a required check, flags and rollbacks.6 min · Intermediate
8. 8The agentic PDLC for business sponsors: ask for two numbersWhat a business sponsor owns in an agentic AI programme: funding past cycle one, the autonomy ceiling, what counts as evidence, and three reports to insist on.6 min · Beginner
9. 9Agentic AI for executives: four decisions only you can makeThe four agentic AI decisions nobody below an executive can make, four questions to ask every cycle, seven red flags, and a first thirty days with no budget.7 min · Beginner

Also on the wiki.