Agent Workflow Designer

Agent Workflow Designer

The agent designs multi-agent orchestration systems using five core patterns: sequential pipeline, parallel fan-out/fan-in, hierarchical delegation, event-driven reactor, and consensus validation. It implements agent routing strategies, circuit breaker reliability patterns, context window budgeting, and cost optimization across LangGraph, CrewAI, AutoGen, and Claude Code agent teams.

Core Capabilities

• Pattern selection & design — sequential pipelines, parallel fan-out/fan-in, hierarchical delegation, event-driven reactors, consensus validation
• Agent routing — intent-based, skill-based, cost-aware, load-balanced, and fallback-chain routing
• State & context management — persistent workflow state, context budgeting, checkpoint/resume, conflict resolution
• Reliability engineering — circuit breakers, retry with backoff, dead letter queues, timeout enforcement, idempotency

When to Use

• Building multi-step AI pipelines that exceed one agent's capability
• Parallelizing research, analysis, or generation tasks
• Creating specialist agent teams with defined roles and contracts
• Designing fault-tolerant AI workflows for production deployment
• Optimizing cost across workflows with mixed model tiers

Clarify First

Before designing the workflow, confirm these inputs. If any is unknown or vague, ASK — do not assume:

• Workflow topology — linear, parallel, tree/delegation, reactive, or consensus (selects which of the five orchestration patterns)
• Framework target — LangGraph, CrewAI, AutoGen, or Claude agent teams (determines the implementation code emitted)
• Reliability & cost constraints — failure tolerance and budget (drives circuit breakers, retries, timeouts, and model-tier routing)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Pattern Selection Decision Tree

What does the workflow look like?
│
├─ Linear: step A feeds step B feeds step C
│  └─ SEQUENTIAL PIPELINE
│     Best for: content pipelines, code review chains, data transformation
│
├─ Parallel: N independent tasks, then combine
│  └─ FAN-OUT / FAN-IN
│     Best for: competitive research, multi-source analysis, parallel code gen
│
├─ Tree: orchestrator breaks work into subtasks dynamically
│  └─ HIERARCHICAL DELEGATION
│     Best for: complex projects, open-ended research, code generation with planning
│
├─ Reactive: agents respond to events/triggers
│  └─ EVENT-DRIVEN REACTOR
│     Best for: monitoring, alerting, continuous integration, chat workflows
│
└─ Verification: multiple agents must agree on output
   └─ CONSENSUS VALIDATION
      Best for: high-stakes decisions, code review, fact checking, safety-critical output

References

Load the reference that matches the task — keep this file lean and pull detail on demand:

• references/orchestration-patterns.md — full implementations of all five patterns (LangGraph sequential pipeline, async fan-out/fan-in, hierarchical orchestrator with dependency batching, event bus, consensus validation). Read after picking a topology from the decision tree.
• references/routing-and-cost.md — intent-based router, context window budgeting (ContextBudget), and the cost optimization matrix. Read when deciding how requests reach agents and how to control spend.
• references/reliability-and-troubleshooting.md — circuit breaker, common pitfalls, best practices, troubleshooting table, and success criteria. Read when hardening for production or diagnosing failures.
• references/subagent-scoping-and-orchestration.md — when to split work into scoped subagents vs one loop; scoping a subagent (minimal tool allow-list, focused instructions, isolated context, return contract); the lead→parallel-specialists→merge pattern on a shared workspace; failure isolation/retries; and multi-agent vs single-agent cost/latency tradeoffs. Read when designing a lead that delegates to specialist subagents.

Tools Overview

Stdlib-only Python CLIs in scripts/ (run with python3, support --json and human-readable output):

• cost_estimator.py — per-step token/cost estimate for a workflow DAG with model-tier what-ifs.
• multi_agent_cost_estimator.py — compares a lead + scoped subagents design (per-role price tier, call counts, token sizes, reasoning-effort multiplier) against a single strong agent baseline, with a per-role breakdown and total-cost projection. Prices are user-supplied with neutral placeholder defaults — pass --price tier=input/output or a JSON price_tiers block with your real rates.
• workflow_validator.py / workflow_visualizer.py — validate and render workflow DAGs.

Common Patterns

• Scoped subagents — split a job into specialists only where responsibilities are genuinely independent; give each a minimal tool allow-list, one-job instructions, an isolated context, and a small return contract, then merge their contracts in the lead on a shared workspace (see references/subagent-scoping-and-orchestration.md).
• Multi-model routing — run the orchestrator on a stronger tier and narrow subagents on cheaper tiers, matching reasoning effort to each role; estimate both topologies with scripts/multi_agent_cost_estimator.py before committing, and keep the single loop if the multi-agent design isn't meaningfully cheaper or faster.