Introducing Refix Convex, our frontier data agent. First on DataAgentBench Introducing Refix Convex, our frontier data agent. First on DataAgentBench

Deploy agents that find
the revenue you’re losing.

Give Refix a goal for any KPI. Without being asked, it digs into your data until it finds what is holding that KPI back and what to change.

Free and takes about a minute.

Used by growth teams at

Growth should not wait for someone to ask.

You connect your data and approve the change, while Refix does the rest. You approve the change. Refix does the rest.

Increase trial-to-paid conversion At a fitness app

33.8% of free trials become paid plans, against a 37% target.

Trial-to-paid

33.8% Today 37% Target

Reaching 37% is worth about $4.4M a year.

The AI coach is a false lead.

Matched on days logged

  • With the AI coach 36.1%
  • Without the AI coach 35.8%

Members who break a streak pay 18%, less than members who never had one.

  • Kept it all 7 days 52%
  • Never started one 27%
  • Broke one 18%

The 0 feels like failing.

Today 0 day streak
The test 3 of 4 days this week
Approve Reject

Trials with the weekly count pay 36.2%, against 33.8% without it.

  1. Built
  2. Shipped to half
  3. Read
  4. Rolled out

About $3.3M more a year

A goal for every KPI you own.

From acquisition to retention, every goal comes with its own playbook. For anything else, describe your goal and Refix writes the playbook.

Your own goal

Reduce subscription churn

Before tracing what changed, Refix separates failed renewals from decisions to leave.

Learn more

Churn playbook

  1. Failed payments Billing
  2. Usage drop Analytics
  3. Price change Billing
  4. Support tickets Support
  5. Release Deployments

At a fitness subscription app

  • A catalog change cut 312 members’ sessions by 52%. $11k/mo at stake.
  • Android v8.2 broke workout sync and cut affected members’ sessions by 44%. $7k/mo at stake.
  • An annual price rise cut renewing members’ sessions by 31%. $19k/mo at stake.

Refix knows your whole business.

Refix builds a full understanding of your business as it works on your goals. Every goal shares it. You never explain your business twice.

Trial conversion

Trials that start a paid plan, out of all trials started.

The goal to increase trial-to-paid conversion starts here.
  • Built from your sources.

    Refix builds it from every source you connect, with no setup project and no context files.

  • Your figures decide.

    A definition counts only when it reproduces the figures your team already trusts.

  • Learns from the work.

    Every investigation, correction, release and result is written back into it.

  • Shared by every goal.

    A new goal starts with it on day one, and questions in Slack use it too.

  • It belongs to you.

    You can see, correct, approve and export it, and nothing changes silently.

Refix Convex is the most accurate data agent. Findings you can act on.

A wrong number sends your team after the wrong fix. That is why Refix works every goal on Refix Convex.

DataAgentBench asks 54 questions across 12 messy, multi-source datasets. Its hints are notes about each dataset.

With its hints, Refix answers 88.9%, first on the leaderboard, ahead of agents built on Claude Opus 5.5 and GPT-5.5.

Without them, Refix answers more than 65%, at least 6.7 points ahead of the best agent that ran without them.

DataAgentBench asks 54 questions across 12 messy, multi-source datasets. Hints are notes about each dataset.

Refix is first on the leaderboard with hints, and 6.7 points ahead of the best agent without them.

Read the full results

LiveSQLBench tests 180 PostgreSQL read questions across 18 business databases.

After correcting broken reference answers, Refix answers 134, or 74.4%. The best model on the published board answers 47.8%.

Read the full results

Questions answered correctly

  1. 88.9% Refix
  2. 88.2% AIDBS Claude Opus 5.5
  3. 86.2% Phoenix-CLI Claude Opus 5.5
  4. 79.3% DataGallery Qwen3.8-Max
  5. 78.5% Spacedock GPT-5.5
DataAgentBench, UC Berkeley EPIC Data Lab and Hasura PromptQL

Your tools wait for a question. Manual analysis runs out of hours.

Refix brings an analyst’s judgement to every KPI, every day.

Analytics and AI tools AmplitudeMixpanelHexDatabricks GenieSnowflake CortexClaudeChatGPT Tools Manual analysis SQL, spreadsheets and dashboards Manual Refix
Investigates every KPI, every day No No Yes
Starts without a question or a ticket No No Yes
Finds the cause nobody asked about No Yes Yes
Learns your business on its own No Yes Yes
Follows each finding through to the result No No Yes
No hiring and no setup project No No Yes

Security and control, built in.

Choose what Refix can access and set the approvals it needs. Review the data and reasoning behind its recommendations.

Read-only by design

Writes are refused at the database, not left to the model.

Approvals you control

Require your team’s approval before Refix takes action in connected tools.

Roles for every teammate

Decide who connects data, approves actions, and manages billing.

Spend you can see

Daily spend in dollars, with an alert before you reach your limit.

Zero data retention

Model providers keep nothing and never train on your data.

  • AICPA SOC 2 SOC 2 Type II*
  • ISO/IEC 27001 2022 ISO/IEC 27001*

* SOC 2 Type II audit under observation. ISO/IEC 27001 certification in progress.

Goals are free. Pay for the work.

Set as many goals as you like. Credits pay for the work Refix does on them.

Enterprise

Custom

For companies that need self-hosting, security reviews and yearly terms.

  • Everything in Pro
  • Air-gapped self-host on Kubernetes
  • Private dashboard and OIDC
  • Your LLM gateway
  • Restricted outbound connections
  • Dedicated onboarding

Before you start.

What growth teams ask before their first goal.

Book a demo

What do I decide before setting a goal?

Choose the KPI, its target and any constraints. Refix brings the playbook, writes the brief and asks only for the data it needs.

What do I connect?

One read-only source is enough to start: product analytics, payments or your warehouse. Refix asks for more only when a finding needs it.

How soon is the first finding?

You connect one source, read-only. Refix opens the goal’s playbook and checks its KPI. It posts in Slack when it has a cause, the evidence and the revenue at stake.

What if our data is messy?

Refix Convex reads the values, not just the column names, and asks your team when a field is unclear. Messy, multi-source data is what DataAgentBench tests, and Refix Convex ranks first on it.

How is a goal different from a dashboard?

A dashboard waits for you to read it. Refix keeps watching the goal’s KPI, works out why it moved across your tools, sizes the revenue at stake and suggests what to do.

What happens after I set a goal?

Refix starts from everything it already knows about your business, reads the evidence for the goal’s KPI, and comes back when it finds a change worth your attention.

Where do findings show up?

In Refix, and in Slack if you connect it. Each finding names the goal, shows the evidence and the money at stake, and suggests a next step.

Can Refix change anything?

Database and analytics access is read-only. Actions in connected tools follow the approvals you set. Nothing changes without your team’s OK.

Do goals share what Refix learns?

Yes. Every goal uses the same ontology, memory and playbooks. Correct a business rule once and every goal uses the correction.

What happens when we use up our credits?

Overage bills automatically, up to a monthly cap your workspace owner sets. Near the cap, Refix checks less often. At the cap, the work pauses until next month, unless the owner raises it. Anyone can still set goals.

Can Refix run in our cloud?

Yes. Enterprise runs in your Kubernetes cluster, on your models and access controls, with no Refix usage bill.

Find the revenue you’re losing.