Curriculum teaching stub for Plan-Execute loops — explicit planning before tool execution. Pattern used in VAP Architecture Review.
▶ Live demo · Architecture · Portfolio · VAP case study
Decompose goals into steps, then execute — safer multi-step enterprise workflows.
Separate planner and executor roles with inspectable plan artifacts and deterministic tests.
venkat-ai.com/work · docs/ARCHITECTURE.md
Org skills: vpeetla-ai-skills. This repo includes .cursor/skills/, AGENTS.md, and CONTEXT.md.
git clone https://github.com/vpeetla-ai/vpeetla-ai-skills.git
./vpeetla-ai-skills/scripts/install.sh --cursor --codex --project .Scope: Curriculum stub with deterministic tests and a live trace viewer — not a production agent fleet. Compose into Venkat AI Platform for governed graphs.
| Component | Status | Notes |
|---|---|---|
| Pattern demo + trace UI | ✅ | Scenario chips · simulated metrics · compose CTA (VAP/OmniForge) |
| Core agent loop | ✅ | Reference implementation |
| LangGraph production graph | 🟡 | Teaching scope — compose into VAP for fleet use |
| MCP tool bridge | ❌ | See LoopForge / VAP MCP docs |
| AegisAI gateway | ❌ | No side effects in pattern demo |
| Pytest regression | ✅ | pytest -q in repo |
Part 3 of 5 in the Curriculum Agent Patterns series.
Curriculum teaching stub (compose into VAP for production graphs) of the Plan and Execute pattern for research, reporting, data analysis, and controlled multi-step workflows.
| # | Pattern | Repository | Use when |
|---|---|---|---|
| 1 | ReAct | react-agent-pattern | Tool use + reasoning loops |
| 2 | Reflection | reflection-agent-pattern | Self-critique and improve output |
| 3 | Plan-Execute | this repo | Decompose goals into steps |
| 4 | Multi-Agent | multi-agent-system-pattern | Specialized role delegation |
| 5 | Swarm | swarm-agent-pattern | Parallel autonomous agents |
▶ Live demo · 📖 Full series roadmap · Compose in production — AI Content Factory (separate repo)
- Planner produces explicit executable steps
- Executor handles one step at a time with observable state
- Observations feed back into workflow state
- Status is inspectable and resumable (production checkpointing mindset)
- Planner produces explicit executable steps
- Executor handles one step at a time
- Observations are fed back into state
- Workflow status is inspectable and resumable
python -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
python -m plan_execute_agent_pattern
pytestRuns without API keys using deterministic stubs.
cp .env.example .envSee docs/LOCAL_DEVELOPMENT.md for production setup.
Business function: Minimal LangGraph teaching stub for one agent pattern (compose into VAP for production).
Staff+ prep crosswalk — playbook · study UI · Practice Arena · org matrix. Only entries this repo honestly exercises.
| Category | Entry | Fit |
|---|---|---|
| System design | Agent tool-use / orchestration (md) | Pattern slice only — not a full platform |
| Coding | Clone a graph (cycle-safe) (md) | Light — graph structure intuition for LangGraph |
- Previous: Reflection Agent Pattern
- Next: Multi-Agent System Pattern
- Full pipeline: AI Content Factory
⭐ Star the repo if this pattern helps your work.