Labs

Purpose-built agents for climate-focused venture firms.

Claude and ChatGPT become climate-competent when Climatalist AI runs behind them: a climate knowledge graph, your firm’s own graph, and agents that traverse both.

See how it works →

Runs inside Claude & GPT/Live in weeks, not quarters/Every claim cited/Discovery at our cost, no obligation

The gap

Confidently wrong on the facts that decide deals.

Screening, diligence and market reads still run on general-purpose AI. Right on the easy things, wrong on the ones that matter: the incentive that just changed, the comparable round that actually closed, whether the technology is even real.

Good enough to draft. Not good enough to act on.

What it is

Your process. Your knowledge. Your tools.

We translate how your firm works into agentic workflows, give them the context including your firms knowledge and our knowledge corpus, and wire in the tools they need to finish the job.

1Intent

Your workflows, encoded.

Your thesis, your rubric, your process, captured as agent workflows rather than prompts someone retypes each time.

2Context

Two context graphs behind every answer.

The Climatalist graph for the climate economy, plus a second graph of your firm's own knowledge: deals, memos, notes and data rooms, all built and kept current by the agents.

3Tools

Connectors that do the work.

Drive, Slack, Notion, calendars, data rooms, your CRM. The agents read, write, and land finished output where your team already works.

How it fits together

1Climatalist MCP
The climate graphThe climate economy, typed, connected, cited.
Your firm's graphYour deals, memos, notes and data rooms.
Agent workflowsYour intent, encoded and customised.
Your AI ecosystemClaudeChatGPT
2Agent runtime
Agent workflow executionThe agent runs the workflow with both graphs behind it, inside the assistant your team already opens.
ToolsGoogle Drive, SharePoint, Notion, Calendar, Airtable, Zoom and more
3Output
Output created
Memos, briefs, screens and models, all cited.
Shared where you work
Into the doc, the deck, the channel, the CRM.

One connection. Everything behind it.

Your firm hooks up the Climatalist MCP once. Behind it we keep both graphs current, the agent workflows improving, and the connectors live, so the stack gets better without your team touching anything.

The agent stack

Six agents for the work you do every day.

A day-one stack, not the final list. Each one tuned to your firm — and we build more as your workflows surface them.

Deal Screener

A one-page screen of a single deal against your rubric: a composite score, a take-the-call or pass recommendation, the questions for the founder call, and the red flags.

Why the context graph matters. Knows whether the technology is credible at the stated readiness and whether the sector is commercially ready, not just whether the deck reads well.

Inbound Monitor

Batch triage of every deck that landed overnight, on the same rubric. You open Slack and know which three of last night's twenty are worth twenty minutes.

Why the context graph matters. Consistent scoring at volume. The strong ones arrive already enriched with funding, competitors, and market context.

Memo Drafter

The IC memo for a deal past screening: full depth, with precedents and a comps table, written in the deal lead's own voice from your call transcripts and diligence.

Why the context graph matters. Written against your firm's actual thesis, process, and prior investments; every figure re-checked against its source, and anything unverifiable left flagged rather than guessed.

Comparables & Benchmarks

Peer rounds, valuations, terms, and precedents for a target: the climate-specific comp set the generic databases don't cover well.

Why the context graph matters. Climate deal data structured by stage, sector, and geography, cross-checked across providers and cited with an access date.

Sector Brief

An accurate, current state-of-market for a sector and geography, on demand, including who raised what, recently.

Why the context graph matters. Your firm's own documented view leads; external research is walled off and labelled. General AI is wrong most of the time on incentives, mandates, and players.

Portfolio Monitor

Parses founder updates into structured KPIs (ARR, runway, burn, headcount, logos, asks) onto each portfolio page, and flags what's material.

Why the context graph matters. Turns unstructured email into queryable portfolio state, with a verbatim quote and source behind every number it writes.

Together: fewer missed deals, less overhead per deal, and a risk-return view you can defend in front of your IC.

The floor, not the ceiling

Custom agents extend the stack to your firm’s workflows.

Deal room diligence reviewFinancial modellingMorning market briefLP updates & reportingLegislative & tailwind trackingGrant & non-dilutive fundingCo-investor & syndication mappingOfftaker / “investomer” mappingTechnology & TRL validationBoard & IC prep
Accuracy

If you can't cite it, you can't act on it.

The success of sector specific agents requires context that can be trusted, which is exactly what generalized AI models are missing.

General-purpose AI

Which legislation could move global feedstock supply for SAF?

“The IRA is probably the single most powerful lever right now — the 40B SAF tax credit (up to $1.75/gallon) and 45Z clean fuels credit are pulling enormous investment into feedstock aggregation infrastructure, particularly for corn ethanol-to-SAF, waste fats, and lignocellulosic pathways…”

40B expired December 2024 — 45Z replaced it with materially different terms, including a reduced maximum credit
Misses the 45Z North American feedstock sourcing rule — the provision most likely to redirect global supply chains after December 2025
Describes UK feedstock eligibility as “relatively flexible” — contradicts the 35% HEFA cap that constrains the dominant pathway by 2040

Identifies the right levers. Misreads several of the settings.

Your agent, on Climatalist AI

Which legislation could move global feedstock supply for SAF?

“From 1 January 2026, 45Z feedstocks must be grown or produced in the US, Mexico, or Canada[1] — a rule that reshuffles global trade flows and advantages domestic ATJ pathways. The UK’s 35% HEFA cap[2] and the EU’s e-fuel sub-mandate (1.2% by 2030, 35% by 2050)[3] signal the same shift: waste-residue and Power-to-Liquid are the only structurally uncapped pathways.”

Correctly separates 40B (expired) from 45Z, noting the OBBBA credit reduction to $1/gallon max
Names the 45Z North American sourcing rule — the near-term provision most likely to cause feedstock market disruption
Covers the full Asia-Pacific mandate cascade — Japan, India, Korea, Indonesia, China — with binding timelines and specific blend targets
Every claim traces to a cited entity your IC can check

An agent you’d stake a capital decision on.

Every claim traces back to a cited entity, connected to the others through climate-specific taxonomies.

How an engagement runs

From a no-obligation discovery to a stack that keeps improving.

We agree what “working” means before you're on the hook for anything. Then we build it, connect it, and keep it sharp.

  1. 00

    Discovery · two calls

    At our cost

    A 2-hour deep dive on your firm, then a 1–2 hour workflow review. You leave with a recommended stack and a proposed tier.

  2. 01

    Roadmap

    Within days

    We agree, up front, on what “working” looks like: the measurable bar the stack has to clear before you're on the hook for anything ongoing.

  3. 02

    Your firm's Graph

    We stand up your second graph: prior deals, memos, thesis notes, and data rooms, structured so agents can traverse it.

  4. 03

    Configuration

    Agent workflows tuned to your thesis and rubric; connectors, scoping, secrets, security, and model routing.

  5. 04

    Live

    In weeks

    Core is running inside the assistant your team already opens.

  6. 05

    Refinement

    Months of real use. We analyse and tune the agents, and add workflows as they surface under your subscription.

Proceed and the discovery cost comes off your subscription. No commitment beyond the discovery until you've seen what “working” looks like for your firm.

What it costs

A subscription that grows with your firm.

Everything runs on a 12-month subscription — both graphs maintained, agents improving, and new frontier models as they ship. No build-and-walk-away.

Core

The standard agent stack, your firm's Graph, and the Climatalist MCP — maintained and current.

By quote · 12 month subscription
The standard investor agent stack
Your firm's Graph, stood up & maintained
Tuned to your thesis & rubric
Connected into Claude or GPT
Climatalist graph — refreshed & current
Agent improvements included
Most firms

Core + Custom

Core, plus 2–3 custom agents built to your specific deal workflows.

By quote · 12 month subscription
Everything in Core
2–3 custom agents to your workflow
Scoped to your deal process
Priced to number & complexity
New agent workflows as they surface

Fully Managed

Everything in Core + Custom, run and improved by us end-to-end.

By quote · 12 month subscription
Everything in Core + Custom
Run and improved end-to-end
Retainer-level service bundled
Ongoing tuning & new workflows

Proceed and the discovery cost comes off your subscription. No commitment beyond the discovery until you've seen what “working” looks like for your firm.

Get started

See it on your own deal flow.

Start with discovery: two calls, run at our cost with no obligation. A working session on your thesis, your rubric and the decisions you’re trying to support, then a walk-through of the workflows we’d map to agents. You leave with a recommended stack, a proposed tier, and an agreed definition of “working”.

Revisit the stack →

Proceed and the discovery cost comes off your subscription.

FAQ

Common questions.

You keep using Claude or GPT, and the agents run inside them. The difference is what sits behind them: your firm's own knowledge, the Climatalist graph, and workflows built around how your firm actually invests. General models are trained on the open web and are confidently wrong on the exact climate facts a decision hinges on.

Everything runs on a 12-month subscription, quoted to your firm. Behind it: the Climatalist MCP as a single connection into the AI tools you already run, with the Climatalist graph, your firm's graph, and your agent workflows behind it. We maintain all of it for the life of the subscription — refreshed intelligence, new and improved agents, new connectors, and new frontier models as they ship. There is no build-and-walk-away option.

It's a structured knowledge graph of the climate economy. Problems, technologies, projects, organisations, policies, capital and financial structures are modeled as typed, connected entities, each tied to the evidence behind it. Built for climate practitioners, using quality data sets. Full methodology on request.

You get the roadmap within days of discovery, and Core is live in weeks, not quarters, because it connects into the assistant you already use. Custom agents and a fully managed engagement run longer, then months of refinement under the subscription.

Discovery is two calls run at our cost, with no obligation: a 2-hour deep dive on your firm, then a 1–2 hour workflow review. You leave with a recommended agent stack, a proposed tier, and an explicit definition of what “working” means for your firm. If you proceed, the discovery cost comes off your subscription. There is no commitment beyond discovery until you've seen that bar met.

Yes. Your firm's graph is yours alone: never pooled, never shared, never used to train anything shared. The Climatalist graph is the shared layer; your knowledge sits beside it and stays separate.