Frame a clearly fictional opportunity and the diligence question.
Engage now
A diligence-workflow review covering source provenance, criteria, assumptions and the committee record.
Inspect
Development prototype
FastAPI and Next.js application surfaces with PostgreSQL, vector-search, and Redis boundaries.
Still to validate
No investment return, predictive accuracy, or decision-quality outcome is asserted.
Validate licensed data coverage, model and score behaviour, reviewer consistency, and operating controls without inferring investment performance.
Source reviewed
The decision behind the system
Can the investment committee follow the reasoning?
A diligence-workflow prototype connecting deal intake, research, scoring, scenarios, investment-committee reporting and portfolio monitoring.
Kairos focuses on investment diligence and committee records. Scores and scenarios support human judgement; they do not establish predictive accuracy or returns.
One diligence path
Move from intake and triage into research, scoring and scenario work without losing the decision context.
Review and reporting
Investment-committee, portfolio and LP reporting surfaces organise findings for human judgement.
Replaceable providers
Data and model adapters, including a deterministic mock path, separate workflow evaluation from live-provider configuration.
Read the complete system walkthrough
Triage
Frame a clearly fictional opportunity and the diligence question.
Research
Assemble authorised research, making provenance and missing sources visible.
Challenge
Review scenarios and criteria without presenting a score as a calibrated forecast.
Record
Preserve the committee’s reasoning and monitoring questions. Live data needs separate configuration and rights.
Inspect the source, test conditions and operating limits in the technical record.
Explore the technical record and evidence
Business ↔ technology bridge · Diligence decision-support experiment
Connect external signals to an investment decision without turning a score into authority.
Explores a reviewable full-stack diligence workflow with visible assumptions and replaceable model providers.
This is a portfolio and source interpretation—not a customer, deployment, certification, or outcome claim.
01
Business pressure
Deal, market, founder, technical, portfolio, and reporting evidence is assembled across disconnected data sources and individual judgement.
02
Product decision
Separate workflow, APIs, persistence, retrieval, scoring, and model providers, including a deterministic mock path for repeatable testing.
03
Technical record
Deal, research, diligence, scoring, portfolio, and report surfaces across FastAPI, Next.js, data, retrieval, and provider-adapter boundaries.
04
Evidence return
Missing sources, conflicting signals, score assumptions, and reviewer decisions return to thesis, diligence scope, and portfolio monitoring.
Repository/runtime boundary
This page interprets source from a separate venture repository. Source presence does not make the venture a service running inside hyperion-consulting.io.
Visitor and client-data AI processing is restricted to Mistral through the governed EU endpoint. Owner-authorized Helio, Search and Product Council paths are enabled. A separate public-source editorial lane uses Anthropic with governed Mistral backup; it receives no website enquiries, client documents or visitor conversations. Deterministic tools remain available when remote AI is unavailable.
Source evidence
What the source actually establishes
A full-stack diligence-workflow prototype with deal, research, scoring, portfolio, and reporting surfaces. Its source demonstrates workflow architecture and provider abstraction; it does not establish investment performance.
Maturity
Development prototype
Evidence review
Source snapshot through
Architecture and product decisions
Separate the browser workflow, API modules, persistence, retrieval, and model-provider layer.
Use a deterministic mock provider so workflow and scoring behaviour can be exercised without a live model.
Position model-assisted scoring as decision support whose assumptions remain visible to an investor.
Inspectable evidence
FastAPI and Next.js application surfaces with PostgreSQL, vector-search, and Redis boundaries.
Backend tests spanning deal, intelligence, diligence, portfolio, and report workflows.
Provider adapters and local container configuration for repeatable development setup.
Claim boundary
No investment return, predictive accuracy, or decision-quality outcome is asserted.
External data coverage and model output depend on the services and credentials configured by an operator.
The repository does not establish a live customer deployment or a production operating record.
Repository evidence is not client, deployment, certification, or outcome evidence.
Architecture
Workflow surfaces from founder cold-email to portfolio monitoring
Three source boundaries: workflow UI, modular APIs, and a replaceable model-provider layer with deterministic test support.
Source map only: a layer can represent implemented code, an adapter boundary, or documented design. It does not assert a configured production service.
01
Layer 1 — Deal Workflow UI
The Next.js source represents pipeline boards, founder review, scoring, competitive mapping, and portfolio-monitoring surfaces. Source presence does not establish live data coverage or investor adoption.
02
Layer 2 — Modular APIs
The FastAPI source represents modules for deal sourcing, due diligence, founder scoring, technical assessment, competitive intelligence, term-sheet drafting, and post-investment monitoring. Stage-calibrated logic — what matters at seed is not what matters at Series C.
03
Layer 3 — Modular LLM Backend
Provider adapters represent Anthropic, Mistral, Ollama, Hugging Face, and deterministic mock paths. Model behaviour, locality, and data handling depend on the selected provider and deployment configuration.
8 scoring dimensions
What the prototype scores, why it scores it, what the data says
The prototype makes scoring dimensions and rubrics explicit so an investor can inspect assumptions instead of treating a model output as a verdict.
Repository surface only: availability, completeness, performance, and operational fitness require separate validation.
DIM 1
Team Quality
01
Domain depth × execution velocity × team-fit signals (co-founder dynamics, prior shipping evidence, hiring track record). Inputs represented in source: LinkedIn enrichment, public-commit cadence, and interview transcripts. A named source is not evidence of live access.
DIM 2
Market Size
02
Bottom-up TAM with sources, top-down sanity check, 5-year growth thesis, regulatory tailwind/headwind. The proposed rubric would penalise 'all of the EU is our market' with a structured why-now requirement.
DIM 3
Product Fit
03
Captures user-research artefacts, retention evidence where available, and the gap between a demonstration and an operable product. The investor remains responsible for the conclusion.
DIM 4
Traction Strength
04
Revenue curve quality (not just absolute number), net dollar retention, sales-cycle compression over time, organic vs paid mix. Stage-calibrated — what matters at seed is not Series A.
DIM 5
Capital Efficiency
05
Burn multiple vs stage, payback period on CAC, runway clarity, prior round price-to-quality ratio. The proposed rubric would flag 'too much capital for the milestone delivered.'
DIM 6
Tech Depth
06
Technical assessment by domain, drafted by the LLM backend with different rubrics for Seed and Series C. It is an input for the investor to inspect, not a verdict on the founder's claimed novelty.
DIM 7
Defensibility (Moat)
07
Data moat depth, switching cost analysis, regulatory moat where applicable (e.g. clinical, defence), network-effect curve shape. The 'why does this not get crushed by Big Tech?' answer.
DIM 8
GTM Velocity
08
Sales motion clarity, ICP discipline, channel quality, founder-led-sales transition plan. The proposed rubric would penalise 'we'll hire a VP Sales to figure it out' answers.
Tech Stack
Built With
Named technologies identify repository dependencies or adapter surfaces; they do not assert a live integration or deployment.
Anthropic, Mistral, Ollama, Hugging Face, and deterministic mock adapter source; availability, locality, and data handling depend on operator configuration in the separate venture repository.