Full accelerator program

The Agentic AI Software Delivery Lifecycle Accelerator Program.

This program trains your team on foundational, operational, and scalable AI across the software delivery lifecycle. The end result is a team with shared AI fluency, agent-ready specs, quality gates, and governed automation practices they can apply to AI-assisted delivery.

View upcoming dates →Private programs →

Agentic AI Accelerator Program

Turn scattered AI usage into a shared delivery system.

1/3 · Foundations

AI Is Already in Your SDLC

A focused two-hour session on context engineering for the agentic SDLC. Prompting is the entry point, but the real skill is knowing what context to give an AI system, how to structure it, how to evaluate the output, and how to turn reusable patterns into skills and tool-connected workflows.

Who it is for

Executives, product leaders, PMs, designers, QA, engineers, delivery leads, business analysts, architects, security stakeholders, and anyone involved in software delivery.

You leave with
  • Explain how the agentic SDLC changes the way software teams plan, build, test, and evaluate work
  • Structure text, screenshots, recordings, tickets, docs, and code as useful context for AI systems
  • Use prompting as one part of a broader context engineering workflow
  • Evaluate AI output critically before trusting, sharing, or shipping it
  • Set up the tools and first reusable skills needed to keep learning beyond the workshop
Private workshop outline
  • The agentic SDLC shift: from deterministic workflows to adaptive AI-assisted work
  • How LLMs use context, constraints, examples, instructions, and multimodal inputs
  • Context engineering: structuring text, screenshots, recordings, docs, tickets, and code as useful AI inputs
  • Prompting as one part of context engineering: prompt anatomy, anti-patterns, and structured outputs
  • Reusable skills, MCP tools, mobile AI workflows, and environment setup
  • How to evaluate AI output before trusting, sharing, or shipping it
Explore full curriculum

The Agentic SDLC Paradigm Shift

  • How traditional software development works: deterministic, operator-centric, and automation layered on top
  • The inversion: automation as a first principle, adaptability over repeatability, and iterability over latency
  • Why this changes how developers, product teams, QA, and leaders need to think and work
  • What to expect from the Foundations track

Mental Models for Working with LLMs

  • How models process context
  • What models know, do not know, and hallucinate
  • Setting realistic expectations about non-deterministic outputs
  • How to decide when to trust, verify, retry, or escalate

Multimodal Inputs

  • Context is not just text: screenshots, recordings, documents, tickets, and unstructured data can all become agent inputs
  • How to think about what you are giving an agent to work with
  • Practical developer examples using product context, UI screenshots, code, and workflow artifacts

Context Engineering

  • What context is and why it matters
  • How prompting fits inside a broader context engineering practice
  • How to structure context for better outputs
  • Context windows, limitations, and trade-offs

Prompt Anti-Patterns

  • Common beginner mistakes
  • Vague prompts vs. specific prompts
  • Over-relying on the model
  • How to write prompts that are useful because the context is clear

Skills, MCP Servers, and Tools

  • What skills are and how they work
  • Building your first reusable skill
  • Skill libraries and organization
  • What MCP is, why it matters, and how to connect your first tool

Mobile AI Workflows

  • Claude and Codex on iPhone
  • Mobile setup and configuration
  • Practical mobile use cases
  • Limitations compared with desktop workflows

Evaluation and Environment Setup

  • How to assess whether an AI response is good
  • Critical thinking about AI output
  • Editor setup, API keys, configuration, and recommended tools
  • Practical exercise: write a prompt that accomplishes a real task using well-structured context

2/3 · Planning Work & Specifications

Make the Work Agent-Ready

An intermediate workshop for people using coding agents who need to turn ambiguous work into clear specifications, structured handoffs, and agent-ready tasks. You will learn how to identify deliverables, organize requirements, apply the five prompting principles, manage context for existing codebases, and decide where humans need to stay in the loop.

Who it is for

Product managers, designers, business analysts, project/program managers, QA, engineering leads, and developers using coding agents.

You leave with
  • Turn vague feature requests into actionable specs for humans and coding agents
  • Use the five prompting principles to create clear, reusable work artifacts
  • Design handoffs and context slices that let agents pick up work cleanly
  • Identify low-risk, high-value Tier 1 agentic tasks in your own codebase
  • Choose when to re-prompt, restart, split work, use worktrees, or pause for human judgment
Private workshop outline
  • Identifying deliverables and breaking down ambiguous requirements
  • The SDLC iteration loop: brainstorming, goals, analysis, planning, and architecture
  • The five prompting principles: description, inputs, outcomes, hints, and research
  • Handoff design, context slicing, and spec-writing templates for agent consumption
  • Tier 1 agentic task taxonomy and working with existing codebases
  • Iteration strategies, human-in-the-loop decision points, skills, tools, token spend, and worktrees
Explore full curriculum

Understanding and Organizing Work

  • Identifying deliverables
  • Breaking down ambiguous requirements
  • Turning vague feature requests into actionable specs

The SDLC Iteration Loop

  • Brainstorming > identifying goals > analysis > planning > architecture
  • Where your spec work fits in a larger agentic pipeline
  • How agents and operators share the loop

The Five Prompting Principles

  • Description: what is being worked on
  • Input items: context, files, and references
  • Outcomes: what you want to accomplish
  • Hints: constraints, boundaries, and additional research

Handoff Design and Context Slicing

  • What the next stage actually needs
  • Structuring handoffs so agents can pick up work cleanly
  • What to include, what to leave out, and why it matters

Spec-Writing Templates

  • PRDs, technical specs, and task tickets formatted for agent consumption
  • Worksheets and domain-specific documents
  • Versioning your prompts as artifacts

Tier 1 Agentic Task Taxonomy

  • The highest-value, lowest-risk tasks to automate first
  • PR summarization, static analysis, documentation creation, ticket drift detection, and test plan creation
  • How to identify Tier 1 opportunities in your own codebase

Working with Existing Codebases

  • Providing codebase context and architectural constraints
  • Communicating conventions and patterns to the agent
  • Managing context for large codebases

Iteration Strategies

  • When to re-prompt vs. start over vs. break into sub-tasks
  • Error recovery and debugging prompts
  • What to do when the agent produces wrong or broken output

Human-in-the-Loop Decision Points

  • Where to pause for review vs. let the agent continue
  • What requirements you should never hand to an agent
  • Recognizing when output needs human judgment

Domain-Specific Items, Skills, and Tooling

  • Worksheets and documents tailored to your domain
  • Reusing and sharing skills across projects
  • Building skills for your specific workflow
  • Choosing the right coding agent tool for the job

Thinking Levels, Token Spend, and Worktrees

  • Understanding model reasoning modes
  • Balancing quality vs. cost vs. speed
  • When to use extended thinking
  • Managing parallel workstreams with worktrees

Assessment: Spec Writing Exercise

  • Submit a spec document for a real or sample project
  • Peer or instructor review
  • Gate to Level 2

3/3 · Creating & Managing Harnesses

Automate Without Losing Control

An advanced workshop for teams ready to create automated agents and production-grade harnesses. You will learn agent architecture patterns, runtime and identity models, skills and subagents, state management, orchestration pipelines, testing, security, telemetry, evaluation, PR review automation, CI/CD integration, SDK usage, plugin development, and the governance needed to run agents responsibly.

Who it is for

Senior engineers, architects, platform teams, DevOps/SRE, QA automation leads, security/AppSec, and engineering leaders creating automated agents.

You leave with
  • Design harness architectures using runtime, identity, registry, and orchestration patterns
  • Build modular skills and subagents that compose into larger automated workflows
  • Implement plan, risk, score, and action loops with clear human escalation thresholds
  • Test, observe, and benchmark agent behavior with regression suites and telemetry
  • Integrate agents into PR review, CI/CD, webhooks, scheduled jobs, SDKs, and plugin systems
  • Apply security, trust boundary, governance, and cost controls to production agent workflows
Private workshop outline
  • Agent architecture patterns: orchestrator/worker, parallel agents, sequential pipelines, runtime, harness, identity, and registry
  • Skills, subagents, OpenCode/PI, state management, and task inventories for automation
  • The plan > risk > score > action loop and QA orchestration case study
  • Testing agents, error handling, retries, security, trust boundaries, governance, and cost management
  • Observability and telemetry as active agent inputs, evaluation, benchmarking, and PR review automation
  • Deployment, CI/CD integration, Claude SDK, plugin development, capstone assessment, and continued learning
Explore full curriculum

Agent Architecture Patterns

  • Orchestrator/worker patterns, parallel agents, and sequential pipelines
  • The runtime / harness / identity / registry model as a transferable architectural pattern
  • How these components compose into a working system

OpenCode/PI

  • Setup and configuration
  • Core concepts and use cases
  • Integration with your workflow

Skills and Subagents

  • Building modular, reusable skills
  • Designing subagents for specific tasks
  • Composing skills into larger workflows

State Management

  • Handling memory and session context
  • Managing state across long-running workflows
  • Context persistence strategies

Identifying Common Tasks for the Agent

  • Task analysis and decomposition using the Tier 1 / Tier 2 taxonomy
  • Patterns worth automating and how to prioritize them
  • Building a task inventory for your team

The Plan > Risk > Score > Action Loop

  • Designing agents that assess a plan before acting
  • Scoring confidence and defining thresholds for autonomous action
  • When to act, when to defer to an operator, and how to implement that decision

Automating Orchestration

  • Building orchestration pipelines
  • Multi-model workflows: routing tasks between models
  • Scheduling and event-driven triggers

QA Orchestration: End-to-End Case Study

  • A fully worked example: trigger > research > plan > risk > score > action > results > gate > iterate
  • How to apply this pattern to your own domain
  • Capstone reference architecture

Testing Agents

  • Unit testing prompts
  • Integration testing pipelines
  • Regression suites for agent behavior

Error Handling and Retries

  • Graceful degradation strategies
  • Fallback logic and retry patterns
  • Logging and surfacing failures

Security and Trust Boundaries

  • Prompt injection risks and mitigations
  • Identity scoping: creating identities per runtime and runtimes per job type
  • Least-privilege tool access and credential handling

Governance and Responsible AI

  • IP, data privacy, and disclosure obligations
  • Organizational policy and compliance
  • Human escalation protocols: designing agents that know when to stop

Cost Management

  • Token budgeting and caching strategies
  • Model selection tradeoffs at scale
  • Monitoring and alerting on spend

Observability and Telemetry as an Active Agent Input

  • Every harness should emit structured logs: sessions, token usage, specs, and work performed
  • Downstream agents querying telemetry to actively improve workflows
  • Identifying context gaps, surfacing process reports, and closing the improvement loop

Evaluation and Benchmarking

  • Measuring agent output quality over time
  • Regression detection
  • Building evaluation datasets

PR Reviews

  • Automating PR review workflows
  • Integrating agents into code review processes
  • Quality gates and approval logic

Deployment and CI/CD Integration

  • Running agents in pipelines
  • Webhooks and scheduled jobs
  • Environment management and Tier 2 deployment patterns

Claude SDK

  • SDK overview and setup
  • Building custom integrations
  • Advanced API usage patterns

Plugin Development

  • Designing and building plugins
  • Plugin architecture and packaging
  • Publishing and maintaining plugins

Capstone Assessment

  • Build and demo a working harness or agent pipeline
  • Peer or instructor review
  • Certification awarded upon completion

Community and Continued Learning

  • Where to go after certification
  • Staying current as models evolve
  • Contributing back to the community

Optional certification (recommended)

Add Certified AI Workflow Architect (CAWA) verification when you buy the program.

The accelerator can be purchased on its own, or with CAWA certification verification included. CAWA adds a practical credential for participants who want proof that they can apply AI-assisted workflow practices to real delivery work.

What Certified AI Workflow Architect (CAWA) verification includes

  • Third-party CAWA verification
  • Downloadable certificate
  • Dedicated verification page
  • LinkedIn badge and shareable credential
  • Certification for prompting, specs, harnesses, evals, telemetry, and governance
Learn about CAWA certification →

Upcoming dates

Prepare your team to apply AI across real delivery work.

Each date includes the complete two-day accelerator. Choose the base program, or register with CAWA certification included.

Private accelerator inquiry

Tell us what your team needs.

Share your team size, preferred format, and timing. We'll follow up with a private program recommendation and team pricing.

Prefer email? Reach us directly at workshops@thisdot.co.

Get a recommendation

Tell us what your team is trying to change.

Share your team size, current AI usage, workflow pain, and timing. We'll recommend the fastest workshop path: a public seat, a focused private workshop, or the full accelerator.

What happens next

We'll review your goals and reply with the best workshop path, suggested audience, and next steps for scheduling.

Prefer email? Reach us directly at workshops@thisdot.co.