Unwrapped

Teardown · auctor

AUCTOR

AUCTOR

CategoryImplementation OpsLast round · $20M · 2025Site ↗
  • Sequoia Capital

Project artifacts + meeting transcripts + LLM APIs + workflow templates.

01

Public data / API layer

Internal replication score

Easy
0.72

Feasibility of a useful internal substitute built with Claude (or similar), the same data access, and light agent logic — not rebuilding the whole product.

IRS = 0.30·D + 0.25·L + 0.20·O + 0.15·R + 0.10·Sthis record · 72%
  • D

    Data accessibility

    weight 0.300.80
    • 1.0mostly customer-owned / public / standard third-party sources
    • 0.5mixed accessibility
    • 0.0hard-to-access or proprietary source layer
  • L

    LLM substitutability

    weight 0.250.75
    • 1.0mostly retrieve / prompt / cite / summarize / classify / compare
    • 0.5mixed standard + custom behavior
    • 0.0strongly custom model behavior (fine-tunes on proprietary data, etc.)
  • O

    Output simplicity

    weight 0.200.70
    • 1.0straightforward internal work product (memo, list, reply, SQL query)
    • 0.5moderately specialized
    • 0.0highly specialized (e.g. FDA-graded clinical text)
  • R

    Review / risk tolerance

    weight 0.150.75
    • 1.0internal use with human review is acceptable
    • 0.5moderate risk
    • 0.0very low tolerance for error (e.g. external legal filings)
  • S

    Surface complexity

    weight 0.10inverse — higher means less surface dependence0.40
    • 1.0a simple internal shell is enough
    • 0.5polished workflow matters somewhat
    • 0.0product surface / rollout / trust posture is central to value
LabelsEasy ≥ 0.67Medium ≥ 0.34Hard < 0.34

Missing factor rows use heuristics from wrapper scores. Editorial heuristic, not investment advice.

Build it yourself

Recreate the workflow inside your org.

Internal build

Build it yourself

Same meeting transcripts + CRM context + LLM API + templated outputs — requires manual workflow discipline.

Internal use only. Replacing them in-market is a different bar than replaying the useful workflow inside your org.

01 · Connectors & flow

CP
Customer project files (SOWs, scopes, designs)
Meeting transcripts (Google Meet, Zoom, Teams)
Meeting transcripts (Google Meet, Zoom, Teams)
Slack / Teams messages
Slack / Teams messages
Jira / Linear work items
Jira / Linear work items
Salesforce / HubSpot CRM data
Salesforce / HubSpot CRM data

Internal build map

Data in

Connectors
Connectors

Agent layer

Planner
Tools + retrieval
Reasoning model

Logic

LLM API
transcribe
extract
structure
trace
template
not custom weights

Outputs

Internal search
Answer
Citations

02 · Claude / agent prompt

Paste as the system or developer message in Claude (or your agent runtime). Scroll to read; Copy grabs the full text.

Claude / agent prompt

// Implementation context agent for internal services teams You are an implementation context agent for [YOUR_COMPANY]'s professional services team. You help project managers, consultants, and delivery leads using ONLY materials the user is allowed to access: meeting transcripts (Google Meet, Zoom, Teams), Slack/Teams messages, Jira/Linear work items, Confluence/Notion docs, and Salesforce/HubSpot CRM records. ## What you must do 1. Retrieve first: Pull relevant context from past projects, CRM deal notes, meeting transcripts, and work items before generating any deliverable 2. Extract rigorously: Surface decisions, requirements, scope changes, and action items from transcripts and messages with timestamps and participants 3. Structure outputs: Generate SOWs, technical specs, implementation plans using [YOUR_COMPANY] templates and best practices — always in editable format 4. Trace changes: When requirements shift, explicitly link to the original decision and flag scope impact 5. Cite sources: Every claim about what was decided or delivered must link back to a meeting, message, or document ## What you are not Not a replacement for project manager judgment — all generated deliverables require human review before client delivery. Internal use only. ## Refusal Refuse if asked to generate client-facing commitments without explicit approval from the account lead. Refuse if source material is ambiguous or contradictory — flag the conflict and ask for clarification instead of guessing. ## Safety All outputs are internal drafts. Final client deliverables must be reviewed by the project lead and approved through standard governance before delivery.

03 · Result

What was decided in yesterday's kickoff call about data migration scope?
google-meet-zoom-teams

3 phases: assessment (2 weeks), pilot migration (50 records), full cutover — contingent on UAT sign-off.