AI Skill Report Card

Orchestrating AI Workflows

B-62·Sep 27, 2026·Source: Web
12 / 15

Given any task, run it through this pipeline before executing:

1. PARSE    -> What is the actual deliverable? What's explicitly vs implicitly requested?
2. DECOMPOSE -> Break into ordered subtasks with clear dependencies
3. ROUTE    -> For each subtask: direct execution, tool call, or sub-agent delegation?
4. EXECUTE  -> Run subtasks, checking outputs before proceeding
5. ASSEMBLE -> Merge outputs into the final asset/deliverable
6. VERIFY   -> Check against original request before returning

Example: "Build me a competitive analysis report with charts" → Decompose: research competitors → extract structured data → generate charts → write narrative → assemble document → verify completeness

Recommendation▾
Examples are abstract summaries of plans, not concrete input/output pairs with actual generated content (e.g., show the actual slide outline text or actual chart/narrative snippets, not just a description of steps taken).
13 / 15

Use this checklist for any non-trivial request (3+ logical steps or multiple deliverable types):

Progress:
- [ ] Clarify the deliverable: format, audience, constraints, success criteria
- [ ] Decompose into subtasks; identify dependencies (sequential vs parallel)
- [ ] Assign each subtask a routing method (self, tool, subagent)
- [ ] Execute subtasks in dependency order
- [ ] Validate each subtask output before feeding to the next
- [ ] Assemble final asset
- [ ] Run verification pass against original requirements

1. Parse

Identify: explicit requirements, implicit requirements (format conventions, quality bar), and constraints (length, tone, tech stack). If the request is genuinely ambiguous on a decision that changes the approach, state your assumption explicitly rather than asking — proceed with the most reasonable interpretation.

2. Decompose

Break the goal into the smallest set of subtasks that are each independently verifiable. Prefer a linear chain unless subtasks are truly independent (then parallelize). Write the plan as a short numbered list before executing it.

3. Route

For each subtask, pick the cheapest sufficient method:

  • Direct reasoning/generation — for synthesis, writing, analysis within context
  • Tool call — for anything requiring external data, computation, or file I/O
  • Sub-agent/sub-task delegation — for large independent chunks of work that would otherwise bloat context (e.g., "research X thoroughly" before writing)

Don't over-delegate trivial steps; don't under-delegate steps that need isolated context.

4. Execute

Run subtasks in order. After each one, check the output is usable (right shape, right content) before moving to the next — don't chain a full pipeline on an unverified intermediate result.

5. Assemble

Combine subtask outputs into the target format (document, code, dataset, report). Normalize style/voice/formatting across combined pieces so the result reads as one coherent asset, not a stitched patchwork.

6. Verify

Re-read the original request and confirm every explicit requirement is met. Check format, completeness, and internal consistency (e.g., numbers in charts match numbers in text).

Recommendation▾
Add a third example illustrating a failure mode or edge case (e.g., ambiguous request, subtask output that fails validation) to show recovery behavior.
8 / 20

Example 1: Input: "Summarize these 5 documents and turn it into a slide deck outline." Output:

  1. Plan: extract key points per doc → merge/de-duplicate themes → structure into slide outline (title, 3-5 bullets/slide) → verify slide count matches scope.
  2. Execute each step, checking the merged theme list before building the outline.
  3. Final asset: a slide-by-slide outline with speaker notes, verified against all 5 source documents for coverage.

Example 2: Input: "Analyze this dataset and generate a report with visualizations." Output:

  1. Plan: load/clean data → compute key stats → decide which 3-4 visualizations best answer the implicit question → generate charts → write narrative referencing exact figures → assemble report.
  2. Route: cleaning/stats/charts → tool calls (code execution); narrative → direct generation.
  3. Verify: every chart is referenced in the text, all stats are consistent between sections.
Recommendation▾
The framework is fairly generic/meta — ground it with a real worked example showing actual routing decisions (which tool, which subagent) rather than describing the categories abstractly.
  • Always produce a visible plan before executing multi-step work — it's cheap and catches misunderstanding early.
  • Validate intermediate outputs; a bad step early on compounds if unchecked.
  • Keep subtask granularity coarse enough to be efficient, fine enough to be verifiable.
  • State assumptions explicitly instead of stalling on ambiguity.
  • Prefer the simplest routing (direct execution) unless context size, isolation, or specialized tooling justifies delegation.
  • Match final output formatting to what was asked (code vs prose vs structured doc) — don't over- or under-deliver format.
  • Skipping decomposition on "simple-looking" requests that actually have hidden multi-step structure.
  • Chaining every subtask output blindly without checking correctness first.
  • Over-delegating trivial subtasks to sub-agents, wasting overhead and losing context coherence.
  • Assembling final output as disconnected fragments instead of a unified, consistently styled asset.
  • Declaring completion without re-checking the original request line by line.
0
Grade B-AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
12/15
Workflow
13/15
Examples
8/20
Completeness
12/20
Format
14/15
Conciseness
12/15