All projects
Multi-AgentOct 2025 – Jan 2026Agentic AI

Pitch Deck Debater

Simulated investor boardrooms with VC, CTO, and Product Lead personas, an adversarial Chain-of-Thought feedback loop, and consensus-voting logic that resolves inter-agent hallucinations.

Pipeline

Pitch upload
VC/CTO/Product agents
Adversarial CoT
Consensus vote
Strategic report

The problem

Useful pitch feedback needs several expensive calendars to align. Founders instead iterate on the opinion of one or two reviewers, and blind spots survive until they meet real investors.

Architecture

End-to-end flow, stage by stage.

  1. 01

    Pitch upload

  2. 02

    VC/CTO/Product agents

  3. 03

    Adversarial CoT

  4. 04

    Consensus vote

  5. 05

    Strategic report

How it works

01

A panel of specialised personas

Eight expert agents — venture investor, CTO, data scientist, product and market voices among them — each analyse the deck from their own mandate, so technical depth and market positioning are judged separately.

02

Structured adversarial debate

Agents challenge each other's readings through Chain-of-Thought exchanges, generating counterarguments that surface blind spots a single reviewer pass would miss.

03

Consensus synthesis

Conflicting recommendations are reconciled by consensus voting into one prioritised report that flags deal breakers, improving measured pitch-resilience feedback by roughly 40%.

04

Slide-level ingestion and audio output

PDF and PowerPoint uploads are parsed slide by slide, Claude Haiku keeps the debate fast, and text-to-speech reads critique summaries aloud while the founder scrolls the deck.

  • Orchestrated VC, CTO, and Product Lead agents to evaluate the same pitch from market, technical, and product perspectives rather than returning a single generic critique.
  • Used adversarial Chain-of-Thought feedback loops to generate counterarguments and strategic pushback, improving measured pitch-resilience feedback by approximately 40%.
  • Maintained state across the debate and applied consensus voting to reconcile conflicting recommendations into one cohesive strategic report.

By the numbers

Review depth versus a single reviewer

Expert perspectives applied

higher is better
Before
1
After
8

Pitch-resilience feedback lift (%)

higher is better
Value
+40%

Turnaround (hours)

lower is better
Before
Days
After
Minutes

What it ships with

  • PDF and PowerPoint upload support
  • Per-slide critique plus unified consensus
  • Deal-breaker detection
  • Audio critique summaries
  • Glassmorphism Next.js interface
ImpactBefore → After
13
Adversarial investor personas
No votingConsensus
Voting resolves hallucinations

Stack

LangChainClaude HaikuFastAPIMulti-AgentCoT Prompting