Agents reason.ax1om predicts.
Trained models for conversion scoring, customer health, and timing, built on your own outcome history, validated, with the result surfaced before anything acts on them, and explained down to the field. Your agents call them over MCP and API.
Your agent: judgment, orchestration, language · ax1om: learned prediction, with the factors behind every number
Three trained model families, one contract.
Train on your outcomes, pass the validation gates, predict with the factors behind it. Your agent learns the pattern once.
Conversion scoring
Which records convert, and the fields behind each score.
Customer health
Which customers are drifting, learned from your own renewals.
Timing
Which months an account is likely to come into market.
For AI agents
What your agent can call over MCP today, and why it needs to.
assess_fit()"verdict": "fit"score_records({ explain: true })How it works, in one screen.
- Step 01
Connect your data
Authorize Salesforce or HubSpot in one OAuth click.
- Step 02
Define what you predict
Pick the object and what counts as a conversion.
- Step 03
Train on your pipeline
ax1om trains a dedicated LightGBM model on your own wins and losses.
- Step 04
Deploy where your team and your agents work
Send scores out by CSV, CRM writeback, live API, or scheduled weekly rescoring.
What your agent can call today
Set up ax1om for me. Fetch https://ax1om.ai/get-started.md and follow it.
{ "mcpServers": { "ax1om": { "type": "http", "url": "https://api.ax1om.ai/mcp", "headers": { "Authorization": "Bearer ax1m_sk_your_key_here" } } }}curl -X POST https://api.ax1om.ai/v1/score \ -H "Authorization: Bearer ax1m_sk_your_key" \ -H "Content-Type: application/json" \ -d '{ "model_id": "mdl_abc123", "records": [ { "title": "VP Sales", "industry": "SaaS", "employees": 250 } ] }'import requests
response = requests.post( "https://api.ax1om.ai/v1/score", headers={"Authorization": "Bearer ax1m_sk_your_key"}, json={ "model_id": "mdl_abc123", "records": [ {"title": "VP Sales", "industry": "SaaS", "employees": 250} ], },)response.raise_for_status()print(response.json())Agents call all three model families over MCP; scoring is live on the API and the CRM writeback today.
The calculator that won’t let your agent lie with statistics
ax1om’s gates stand between raw data and a callable model. Leakage detection flags fields that give away the answer before training. Label-maturity checks catch outcomes too recent to learn from. Validation gates every model and surfaces the result before anything acts on it, and every prediction ships with the SHAP factors behind it, so a human can audit what the agent acted on.
This is not agent moderation. Moderation polices what a model says; these gates police the statistics, the leakage and immature labels that make a model plausibly wrong. The validation state is surfaced at every point an agent or a person acts on a model, and how to deploy on it is your call.
Backed by enterprise-grade infrastructure
ax1om runs on providers that hold independent SOC 2 Type II, ISO 27001, ISO 27017, ISO 27018, and PCI DSS Level 1 certifications. Our own SOC 2 Type II audit begins Q4 2026.
Google CloudSOC 2 Type II · ISO 27001 · ISO 27017 · ISO 27018
SupabaseSOC 2 Type II
VercelSOC 2 Type II · ISO 27001
CloudflareSOC 2 Type II · ISO 27001
StripeSOC 2 Type II · PCI DSS L1
SentrySOC 2 Type II
- SOC 2 Type IIAudit Q4 2026
- GDPRDPA with SCCs available
- CCPACompliant as service provider
- US data residencyUS regions only
You see every factor behind every score, and nothing routes until you say so. Your rules, your thresholds, your writeback.
What’s new
- Conversion anchor: the configured success date drives the label
Training now reads the success date you configured, rather than inferring one, when it builds the conversion label.
- A lifecycle cookie, so ax1om.ai knows which call to action to show
The app sets one first-party cookie carrying your stage and tier, four possible words and no identifier, so the docs site stops pitching a signed-in customer.
- The MCP tool table on the site derives from the server registry
The published tool reference is generated from the server's own tool manifest, and the build fails if the two disagree.
- A confirmation door for proposed nuances
Proposed nuances can now be confirmed or declined by an org owner or admin. Only a confirmed entry changes a number, and an agent never confirms.
What teams ask before they start.
You know what your team, and now your agents, could do with prioritization they actually trust. Everything you've tried either can't be explained or can't be maintained. That's not a you problem; it's how the tools were built.
Can my AI agent call ax1om?
Yes. Conversion scoring is live on ax1om’s MCP surface today. Point an MCP client at it - Claude Desktop, Claude Code, and Cursor all work - and your agent can check fit, prepare a scrubbed export, train a model on your own conversion history, and score records live with the factors behind each score. Agents authorize with per-user OAuth: you approve exactly what the agent may do, and you can revoke the grant at any time. Connecting costs nothing on any tier; live scoring runs on your plan, on Pro and above, because an agent calls the same metered route your own service would. Customer health and timing are on the surface too. Health scores live the same way, returned as renewal risk. Timing stops one step short by design: an agent configures it, refreshes it and reads it per horizon, but cannot score an account on demand, because timing refreshes on a dispatched run rather than per request.
Does the LLM see my CRM data?
Only what you choose to send, and the workflow is built scrub-first. The export spec defines which field classes may leave your org and which never may, and direct identifiers are dropped or hashed before anything uploads. The local tools run entirely on your machine and never touch the network, so an agent can prepare and lint an export with nothing leaving the org. What comes back to the agent is scores and factors, not your records. Your models train on ax1om’s infrastructure, on your data only, and are never shared across customers.
What happens when a score is wrong?
Scores are advisory, never automated actions, so a wrong score costs you a judgment call, not a lost deal. Every score ships with the SHAP fields that drove it, so a rep can see the reasoning and override it. ax1om also down-weights sparse and noisy fields automatically and flags likely target leakage before training, which catches the most common causes of confidently-wrong scores up front.
How much control do we keep over routing?
All of it. Nothing routes until you say so. You set the thresholds, you designate which CRM fields ax1om writes to, and scores stay advisory: ax1om never takes an action on a record by itself. Every score ships with the SHAP fields behind it, so you can audit a decision before you build a rule on it.
Will our reps actually use the scores?
That is what the explanation is for. The line of factors behind a score is written into a field on the Lead or Account record your reps already work, so there is no new tool for them to adopt.
Ready for numbers your agents didn’t make up?
Connect your data, train on your own outcomes, and every number your team and your agents act on is trained, validated, and explained.