executive intake · v1.0 · 19 fields · 4 rows · 3 passes

What Happens to User Input

The full trace: 19 executive intake fields through parsing, scoring, multi-pass analysis, and roadmap generation. Every heuristic, decision, and confidence signal at the point it is injected.

19
input fields
4
context rows
12
heuristics
3
LLM passes
95
confidence cap
01What goes in — the 19-field executive intake
About your business
business_name, industry, employee_count, what_they_do, what_makes_different
What’s working
biggest_bottleneck, time_consuming_tasks, success_definition, top_priorities, business_impact
How work gets done
founder_role, team_description, delegation_gap, decision_style
Tools & guardrails
essential_tools, document_storage, compliance_requirements, investment_comfort, non_negotiables
Dysfunctionality
knowledge_in_heads, unwritten_rules, rework_loops, broken_handoffs, founder_blocking, decision_latency …
02Parse & classify — 19 fields into 4 context rows

Each of the 19 fields maps deterministically to one of four org_context rows. No AI here — _create_org_context_entries() unpacks the flat dict into typed records (title, content, content_summary). The business name becomes a slug and an organizations row (org_type="smb") with the submitter added as admin, best effort.

Context typeSource fieldsExample content
company_profilebusiness_name, industry, employee_count, what_they_do, what_makes_different“Founded in 2012, Acme produces industrial adhesives for the automotive sector with 47 employees.”
strategic_goalsbiggest_bottleneck, time_consuming_tasks, success_definition, top_priorities, business_impact“Their biggest bottleneck is estimating — complex quotes take 3–4 hours and only the founder can price them.”
smb_operationsfounder_role, team_description, delegation_gap, decision_style“The founder spends 60% of time on estimating. Team of 12 includes 4 crew leads.”
smb_constraintsessential_tools, document_storage, compliance_requirements, investment_comfort, non_negotiables“They use QuickBooks and Excel; documents live in a shared Drive, inconsistently organized.”
03Confidence scoring — how much we trust the output

Every empty field reduces confidence — and each reduction is tied to a specific, hand-authored impact statement naming exactly what the roadmap can’t say because of that gap. Not a generic score: a gap-by-gap audit trail.

Section score = 20 × (filled / total fields in section)
Raw total = sum of 5 section scores
Final = min(Raw total, 95)
Level = high ≥75  |  medium ≥50  |  low <50

The cap at 95 is deliberate: perfect confidence is a false signal. Even fully filled, self-reported data carries uncertainty. Each of the 19 fields has a unique hand-written impact in _executive_gap_impact() — e.g. “without the founder’s day-to-day role, the roadmap cannot identify delegation opportunities.” High means well-grounded; medium, direction sound but recommendations may shift; low, a conversation starter whose gaps become cohort exercises.

04Multi-pass LLM analysis — three agents, three perspectives

A single “write a roadmap” prompt is fragile — it skips evidence, invents details, or collapses into generic advice. Three independent passes with narrow lenses force claims to be grounded before synthesis. If a pass fails, the pipeline degrades gracefully.

Pass 1 — Dysfunctionality traits agent · temperature 0.2

Input: all four context rows + confidence. Produces a 5×5 maturity assessment scored with specific intake evidence, dysfunctionality severity on five 1–10 axes, ranked confidence gaps, and boundary cases where better data would shift a level.

Pass 2 — Roadmap synthesis agent · temperature 0.2

Input: Pass 1 traits + context + confidence. Produces three strategic movements (each with risk signals, dependencies, success indicators), the honest truth, the one move, and a before/after picture.

Pass 3 — Prose roadmap agent · temperature 0.2

Input: Pass 1 + Pass 2 + context + confidence. Renders the maturity snapshot with a stage-by-stage gap map, the one move, what changes, the honest truth, and a source manifest of which fields informed which claims.

Graceful degradation: Pass 1 fails → single-pass Pass 3. Pass 2 fails → Pass 3 on Pass 1 data only. Each pass is persisted independently (adoption_roadmap_traits, adoption_roadmap_synthesis) for audit.

05Validation, persistence & output
JSON validation
Output validated against the expected schema. Up to 2 automatic retries on malformed JSON or missing fields, each with the specific validation error.
Persistence
adoption_roadmaps (final roadmap), _traits and _synthesis (audit), smb_intake_submissions → completed.
The 5-page roadmap
≈1,900 words of founder-ready prose: maturity placement, bottleneck dimension, stage-gap map, three movements with risk signals, the one move, the honest truth, what changes, and the source manifest.
Confidence ≠ maturity
Confidence says how much to trust the roadmap; maturity says where the organization sits. A low-confidence roadmap with high maturity is flagged suspect. Each Pass 1 dimension score carries a confidence_modifier for how far placement could shift.
06What the pipeline does not do
Guess at missing data

Empty fields are named as gaps, never inferred. The no-assumptions rule is enforced at every pass.

Recommend specific AI tools

It says “you need a way to capture estimating rules,” not “buy Tool X.” Tool names without context are forbidden.

Claim 100% confidence

The 95-cap keeps the system honest: this could always be sharper.

Use one framework for everyone

The model is universal but every score is grounded in that organization’s intake — two businesses at “AI Ready” got there differently, and the output says so.

07Every heuristic & decision point
#Decision pointWhat it doesWhere it lives
1Field completeness checkBinary — is each field non-empty? Drives confidence and gap analysis._compute_confidence_executive()
2Section weighting5 sections × 20 pts, equal — company profile matters as much as dysfunctionality._compute_confidence_executive()
3Confidence cap at 95Deliberate ceiling — even 19/19 fields carry inherent uncertainty.min(total, 95)
4Gap impact mapping19 hand-authored impact statements, each naming what the roadmap can’t determine._executive_gap_impact()
5Confidence tieringHigh ≥75 / Medium ≥50 / Low <50, each with a plain-language summary._executive_confidence_summary()
6Maturity bottleneck principleOverall maturity = lowest dimension. Prevents cherry-picking the strongest.maturity_model prompt section
7No assumptions ruleBefore every claim: did they tell us this? Otherwise flag it as a gap.design principle #5
85×5 dimension scoringEach dimension at each level, evidence required, boundary cases flagged.Pass 1 agent
9Dysfunctionality severity 1–10Five axes scored independently, not averaged; high signals trigger specific moves.Pass 1 agent
10Multi-pass triangulationPass 1 → 2 → 3, each challenged to challenge, graceful degradation._generate_roadmap_background()
11Jargon banNo LLM, API, vector database, embedding, token, agent, platform — enforced and retried.design principle #4
12Source manifestEvery claim traces to a specific intake field; an audit trail for system and reviewer.output JSON

19 fields enter → deterministic parsing into four context records → confidence scoring with hand-authored gap impacts → three-pass LLM analysis grounded and cross-validated → JSON validated with retries → persisted with a full audit trail → a 1,900-word founder-ready roadmap with maturity placement, bottleneck identification, stage gaps, movements, the honest truth, and a source manifest of which intake field informed every claim.