Decision Log & Template

This turns the playbook from something you read into something you use: a short record, one per task, of which framework or stack you picked, why, and how it went. It's quick to fill in, and it builds into your own evidence base over time. It also holds the routine for keeping the playbook up to date.

When to log. Any time you commit a real prompt design to a task or product. Skip it for quick throwaways.

Generate an entry from your notes#

Paste your recipe card and your eval result, and copy a prompt that drafts the log entry and pulls out the reusable lesson (and whether it belongs in the Anti-Pattern Gallery). It runs in your own chatbot, no API. The manual template is below if you would rather fill it in yourself.

Copy-paste entry template#

markdown### [YYYY-MM-DD] {{Task / feature name}}

**Task.** <one-line description of what the LLM must do>
**Constraints.** latency budget / cost ceiling / accuracy bar / has-verifier?

**Recipe (one framework per axis, build order; skip what you don't need):**
- E Abstraction   → <Step-Back / Analogical / skip>
- D Decomposition → <Least-to-Most / Plan-and-Solve / Self-Ask / Pipeline w/ Intermediate Artifact / skip>
- A Topology      → <CoT / Thread of Thought / Tree of Thoughts / Graph of Thoughts / Skeleton>
- C Grounding     → <PAL / ReAct / CoVe / PAL-in-ReAct / skip>
- F Self-Eval     → <Self-Refine / Reflexion / skip>
- B Sampling      → <Self-Consistency / USC / skip>
- G Steering      → <Directional Stimulus / skip>

**Chosen stack.** <e.g., Step-Back × ReAct × Self-Consistency(N=7)>
**Alternatives rejected.** <framework, why not (cost / mismatch / overkill)>

**Result.** shipped? · eval score (from [[Reasoning-Framework-Eval-Rubrics]]) ·
measured cost/latency vs. budget
**Lesson.** <what you'd change next time, feeds the anti-pattern gallery>

Worked example entry#

markdown### [2026-07-01] Vendor security-posture summarizer

**Task.** Summarize security posture across 6 audit reports; flag contradictions.
**Constraints.** No hard latency bar; factual accuracy critical; sources provided.

**Recipe (build order):**
- E Abstraction   → skip (no governing rules to state first)
- D Decomposition → skip (one synthesis, not dependent sub-steps)
- A Topology      → Thread of Thought (six long reports to digest, section by section)
- C Grounding     → Chain-of-Verification (factual stakes high, verify each claim)
- F Self-Eval     → skip (CoVe already does the checking)
- B Sampling      → skip (no discrete answer to vote on)
- G Steering      → skip

**Chosen stack.** Thread of Thought × Chain-of-Verification.
**Alternatives rejected.** Plain CoT (loses mid-context evidence); Self-Consistency
(no discrete answer to vote on).

**Result.** Shipped. Eval 11/12 (Efficiency 1, verify pass verbose). Latency fine.
**Lesson.** Draft overstated a claim ("fully remediated"); CoVe caught it. Add
"quote the source verbatim" to the thread phase to prevent paraphrase drift.

Log#

<!-- Newest first. Append entries above this line using the template. -->

Keep-the-playbook-current workflow#

The playbook goes stale if new techniques and your own lessons never flow back in. Keep it fresh with a light routine:

1. After each decision, once you've written a Lesson, ask whether it's a mistake that could happen again. If so, add a case to Reasoning-Framework-Anti-Pattern-Gallery.
2. Monthly (5 minutes), skim your recent entries. If one framework keeps losing, revisit its row in the choice matrix.
3. When you find a new technique, before adding it to Advanced-AI-Reasoning-Framework-Playbook, place it on one of the 7 axes. If it doesn't fit any axis, it's either a genuinely new axis (rare) or a variant of something you already have (common), file it as Tier-2 unless it earns the full write-up.
4. Promotion rule, a Tier-2 variant moves up to a full Module 1 entry only after you've logged at least 2 real tasks where it was the right first choice.