New and updated lessons on the agentic PDLC, by SkyWays Consultancy https://akash-coded.github.io/aws-bedrock-agentcore-strands/feed.xml 2026-10-08T00:00:00Z https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/what-is-the-bmad-method/ 2026-10-08T00:00:00Z

The BMAD Method as it installs today: five named agents, skills in your coding tool, one Build loop that sizes itself. When its trail pays, and when not.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/what-is-the-agentic-pdlc/ 2026-10-03T00:00:00Z

The agentic PDLC is a four-phase lifecycle (Frame, Design & Spec, Build & Prove, Run & Learn) for software in which an AI model does part of the work.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/what-is-a-forward-deployed-engineer/ 2026-10-03T00:00:00Z

What a forward deployed engineer (FDE) does, where the role came from, how it differs from a solutions architect, and why AI labs now hire FDEs.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/the-hard-gate/ 2026-10-03T00:00:00Z

Only one hand-off in the agentic PDLC halts the build. Which decisions are hard, which run behind a placeholder, and the four questions that tell them apart.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/the-evidence-pack/ 2026-10-03T00:00:00Z

The minimum artefacts owed at each hand-off of an agentic AI project, and the one column that separates a real gate from a formality: enforced, or only written?

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/the-eight-loops/ 2026-10-03T00:00:00Z

Eight loops turn the agentic PDLC from a line into a ring. Five close themselves; three (cost, incident, governance) close only if a named person makes them.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/skyways-case-study/ 2026-10-03T00:00:00Z

A worked agentic AI case study: a fictional airline's rebooking assistant in thirteen episodes, from 31 requirements on day 1 to two numbers on day 90.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/shadow-mode-and-cutover/ 2026-10-03T00:00:00Z

How to launch an AI agent safely: run it in shadow beside the people doing the job, cut over at 5% per action, widen on evidence, and rehearse the way back.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/review-ai-generated-code/ 2026-10-03T00:00:00Z

When agents write most of the code, review is the bottleneck. How to band changes by what they touch, route readers by band, and halve a review queue.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/p0-frame/ 2026-10-03T00:00:00Z

P0 Frame is the agentic PDLC's first phase: turn a request into a measured pain, test whether it needs AI at all, size the value and set autonomy per action.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/one-lifecycle-for-every-method/ 2026-10-03T00:00:00Z

Where AWS AI-DLC, Kiro, Spec Kit, BMAD, Scrum, Shape Up and stage-gate sit on the agentic PDLC's four phases, and the decisions none of them makes.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/how-to-run-an-agentic-ai-project/ 2026-10-03T00:00:00Z

Twelve steps from a vague request to an AI agent in production that someone can defend: who owns each step, what it produces, and what is never delegated.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/how-accurate-must-an-ai-agent-be/ 2026-10-03T00:00:00Z

An AI agent's accuracy bar comes from money, not a round number: divide the damage of a wrong answer by the saving of a right one, per slice.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/forward-deployed-engineer-interview-questions/ 2026-10-03T00:00:00Z

Ten forward deployed engineer (FDE) interview questions (discovery, demos, evaluation, debugging, design, handover and pushback) with strong answers.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-incident-postmortem/ 2026-10-03T00:00:00Z

An AI incident postmortem asks which enforced control would have made it impossible, not who was careless. Five moves, from the layer table to the brief.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-guardrails-that-hold/ 2026-10-03T00:00:00Z

A limit in a prompt can be talked past; a limit in a tool's signature cannot. Six controls that make an AI agent's boundaries real, with a test for each.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-drift-monitoring/ 2026-10-03T00:00:00Z

AI drift is behaviour changing with no deploy and no error. Why accuracy alerts arrive late, what to watch instead, and the two thresholds that catch it.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-dlc-vs-aidd-vs-agentic-sdlc/ 2026-10-03T00:00:00Z

AI-DLC, AIDLC, AIDDLC, AIDD, agentic SDLC, spec-driven development and BMAD: who coined each term, what it names, and the question it answers.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-dlc-for-forward-deployed-engineers/ 2026-10-03T00:00:00Z

How 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-solution-architects/ 2026-10-03T00:00:00Z

What a solution architect decides in agentic AI: which steps may be probabilistic, how many agents, the authority budget, where caps live, and the records.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-qa/ 2026-10-03T00:00:00Z

How 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-engineers/ 2026-10-03T00:00:00Z

How 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-business-sponsors/ 2026-10-03T00:00:00Z

What 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-ai-engineer-interview-questions/ 2026-10-03T00:00:00Z

Ten agentic AI engineer interview questions: the agent loop, enforced limits, tool design, MCP security, multi-agent systems, evaluation and runaways.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/why-agentic-ai-projects-fail/ 2026-10-02T00:00:00Z

Gartner expects over 40% of agentic AI projects to be cancelled by 2027. The seven failure modes behind that, why normal checks miss them, and the fix for each.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/what-is-spec-driven-development/ 2026-10-02T00:00:00Z

Spec-driven development means writing the spec before the code and building from it with AI. How Kiro and GitHub Spec Kit do it, and the honest critiques.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/what-is-aidd/ 2026-10-02T00:00:00Z

AI-driven development (AIDD) is the everyday craft of building software with coding agents: context files, story files, exact code first, and review by risk.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/what-is-ai-dlc/ 2026-10-02T00:00:00Z

AI-DLC is AWS's AI-Driven Development Life Cycle: AI proposes and people decide, across Inception, Construction and Operations, in bolts of hours or days.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/team-structure-for-agentic-ai/ 2026-10-02T00:00:00Z

No new roles, none disappears, but two boundaries move. How to organise product teams, a platform team and governance for agentic AI, and where the seams go.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/rolling-out-agentic-delivery/ 2026-10-02T00:00:00Z

A 90-day plan for rolling out agentic AI delivery: pick for provability, write the artefacts, build in slices, shadow beside the humans, report two numbers.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/prove-ai-accuracy/ 2026-10-02T00:00:00Z

A score from a test set is an estimate with a width. How to report the lower bound, count the cases a slice still owes, and give a verdict a sceptic accepts.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/p3-run-and-learn/ 2026-10-02T00:00:00Z

P3 Run & Learn covers cut-over, rollback, drift and cost for AI agents in production, and the two-number report that decides whether the programme survives.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/p1-design-and-spec/ 2026-10-02T00:00:00Z

P1 Design & Spec turns a framed problem into an eight-field spec with EARS acceptance, a bar per slice and an authority budget an AI agent can build from.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/measure-ai-productivity/ 2026-10-02T00:00:00Z

Measure AI productivity against a baseline taken before the pilot, and report the saving beside the spend, review hours and re-runs, with a worked example.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/how-to-answer-ai-interview-questions/ 2026-10-02T00:00:00Z

Six frameworks for AI interview questions: design, good enough or not, wrong answers, cost, incidents and behavioural stories, each with a worked example.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/how-this-tutorial-works/ 2026-10-02T00:00:00Z

Every lesson opens with the answer, shows it as a picture, lets you try it, and credits its sources. Here is why, with the research behind each choice.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/how-much-process-does-a-change-need/ 2026-10-02T00:00:00Z

Size process by a change's risk, not its size: four questions choose shallow, standard or deep work, and one trigger raises the depth mid-flight.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/genai-engineer-interview-questions/ 2026-10-02T00:00:00Z

Ten deep GenAI engineer interview questions on RAG failures, evaluation, fine-tuning, latency, cost, prompt injection, structured output and memory.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/evolution-of-the-pdlc/ 2026-10-02T00:00:00Z

How the product lifecycle evolved from waterfall to agile, DevOps and agentic delivery, and what genuinely changes when a model does part of the work.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/cut-delivery-time/ 2026-10-02T00:00:00Z

AI makes building fast; delivery is more than building. What compresses, what compresses only by design, what never compresses, with the arithmetic for each.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/bolts-vs-sprints/ 2026-10-02T00:00:00Z

When AI builds a story in hours, a two-week sprint leaves it idle. How to plan in bolts: one unknown each, cut by dependency, integrated the same day.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/aws-generative-ai-interview-questions/ 2026-10-02T00:00:00Z

Ten AWS generative AI interview questions on Bedrock, AgentCore, Strands, Knowledge Bases, Guardrails, IAM, cost and resilience, with architecture answers.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-product-manager-interview-questions/ 2026-10-02T00:00:00Z

Ten deep AI product manager interview questions on AI judgement, design, metrics, evaluation, strategy, cost and leadership, each with a framework and answer.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-governance-gates/ 2026-10-02T00:00:00Z

Five gates govern an AI agent from idea to wide use: intent, plan, behaviour, release and expansion. Who owns each, and the evidence each one needs.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-delivery-maturity-model/ 2026-10-02T00:00:00Z

An AI maturity model that counts controls, not tools: six controls, each proven by a test you run in minutes, and how to pick the next one to build.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/ai-agent-costs/ 2026-10-02T00:00:00Z

An AI agent's bill rarely has one cause: context, model tier, cache and retries multiply. How to find each in the per-call log and fix them in order.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-program-managers/ 2026-10-02T00:00:00Z

How a program or delivery manager runs agentic AI delivery: the board, the cadence, the decision log, the review queue, gate conditions and two numbers.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-product-managers/ 2026-10-02T00:00:00Z

What 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-for-devops/ 2026-10-02T00:00:00Z

What 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-kanban-board/ 2026-10-02T00:00:00Z

A project board for AI agent delivery: evidence as the exit rule for every column, risk bands as swimlanes, and WIP limits set by review capacity.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-delivery-cadence/ 2026-10-02T00:00:00Z

The operating rhythm of an agentic AI project: what runs every day, on every change, every week, every cycle and every quarter, and who owns each check.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-ai-for-executives/ 2026-10-02T00:00:00Z

The 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.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/p2-build-and-prove/ 2026-09-24T00:00:00Z

P2 Build & Prove builds an AI agent in bolts of hours or days, gates every merge on a per-slice bar and ends with a shadow run beside the people doing the job.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-pdlc-exercises/ 2026-09-24T00:00:00Z

Twelve agentic AI delivery exercises with worked answers, three per phase: AI-fit, value, gates, bars, chains, bounds, cases, queues, bills, drift, controls.

Akash Das https://akash-coded.github.io/aws-bedrock-agentcore-strands/learn/agentic-delivery-simulator/ 2026-09-24T00:00:00Z

A free, browser-only agentic AI workbench: 13 dated episodes, 9 decision simulations, 17 prefilled tools and an evidence pack that downloads as one file.

Akash Das