recon
0

Shared customer memory for B2B SaaS

Stop asking around.
Start knowing every customer.

The shared customer memory for B2B SaaS. So your team and their AI agents get answers without digging through tools.

ask recon

1 of 6

Brief me on Acme before my call tomorrow.

Enterprise plan, 52 seats, 17 active this month. Two open tickets (search regression, kanban bug) filed by VP Ops. Renews May 6.

HubSpotStripeIntercomPostgres

Product overview

What Recon is, end to end.

A short walkthrough of what Recon reads, the shared customer memory it builds, and how monitors and advisories turn that memory into the next action.

How it works

Three surfaces. One shared memory.

Memory under Accounts. Watch under Missions. Action under Advisories.

01Memory

Every customer remembered.

Plan, usage, recent issues, admins, opportunities — one cited file per account.

02Watch

Catches changes before you do.

Recon watches the accounts that matter. Pings you when usage drops, tickets land, or renewals slip.

03Action

Drafts the next move with evidence.

When something is worth doing, Recon proposes the action with cited evidence. You approve before anything writes.

Remember every customer.
Catch every change.

One shared memory. Recon remembers every customer, watches the accounts you care about, and proposes the next move with evidence attached.

Shared customer memory

A cited file on every customer

Every customer gets a cited history: plan, usage, admins, incidents, tickets, billing, adoption, risks, and opportunities. Ask questions when you need to, but the memory is already there.

Current stateChange logRelationshipsAdoptionIncidentsOpportunities
Full audit trail

See every step

Every SQL query run, every file read, every ticket checked — visible and auditable. No black boxes.

1
Queried subscriptions table
2
Cross-referenced 8 Intercom tickets
3
Found root cause in webhook handler

Connect product reality

Postgres, Supabase, GitHub, Linear, Intercom, Zendesk, HappyFox, Sentry, Stripe, HubSpot, and docs. Recon reads the systems where customer truth actually lives.

Take it with you

Save Recon's answers as a Notion page, a Linear ticket, a Slack thread, or a downloadable file. No copy-pasting across tools.

Add ground truth

Upload docs, notes, PDFs, or call transcripts when they matter. Recon folds them into customer memory and cites them in answers.

Customer monitors

Define what matters in plain English. Recon keeps an eye on specific customers, usage drops, renewals, issues, and spikes.

Daily reflection

Daily synthesis reads across monitors, investigations, and account history to update health, risks, and opportunities.

Advisories

Actionable recommendations with evidence attached. Create a ticket, investigate further, start a monitor, or prep outreach after approval.

Reads from the systems you already use

One memory, built from your real systems.

RoadmapBuilding an MCP server so Claude Code, Cursor, and ChatGPT can read your customer memory.

Security and trust

Production access
without the production risk.

Recon reads your database, code, errors, tickets, and billing to remember every customer. That access is enforced read-only, gated by approval for any write, and logged end to end.

Read the full security overview
01

Read-only by default

Database access through a dedicated read-only Postgres role. Writes require human approval.

02

Cited and audit-logged

Every claim links to its source. Every query and tool call lands in an append-only log.

03

Sandboxed execution

Each investigation runs in an ephemeral E2B Firecracker microVM, torn down on idle.

04

AES-256 encrypted secrets

Connection credentials encrypted at rest. End users never see raw keys.

05

Bring your own LLM key

Your Anthropic, OpenAI, or Google key. Recon never proxies tokens through a shared account.

Simple, transparent pricing

No per-seat charges. Unlimited users via Slack. Bring your own API key for inference, so tokens are billed by your provider, not us.

Slack-native
Unlimited members
All integrations
Sandbox execution
Pro
$99/ month

For one team

  • 100 conversations / day
  • 1 workspace
Popular
Business
$199/ month

For multiple teams

  • 500 conversations / day
  • 5 workspaces
  • Audit log
  • Priority support

Every plan includes a guided setup call with our team.

What is a conversation?

Anything you ask Recon. An investigation, a monitor run, or a follow-up question all count as one conversation, regardless of how many steps Recon takes to answer. Failed conversations (sandbox errors, integration auth issues) do not count.

Common questions

The things every team asks before connecting.

Give your team a shared customer memory.

One call, your systems connected, every customer remembered.

Most teams are live in under 30 minutes.

Curious? Ask an AI about Recon