01 · Inbound
Leads stop dying in the shared inbox
A B2B client was losing good inbound to manual triage. **We wired intent checks to CRM tasks, with a human step for anything unclear.** Tickets dropped 38% in 60 days.
AI work
The pilot stalled. The inbox did not.
Your team already tried something with AI. It demoed well and never reached production. We map the repeat work, name who handles exceptions, and ship into the stack you run.
Named lead
Same person from first call to go-live
10–20d
Usually live in two to three weeks
No platform
No three agents and a monthly fee
Wrong fit
Not for you if you want a platform.
If you are still comparing AI vendors on feature checklists, you do not need us yet.
We usually get the call after the pilot. The vendor has moved on. The report sits in a shared drive. Nothing is wired into your CRM, legal has not signed off on data routing, and nobody knows who gets paged when it breaks at 2am.
We show up with one named engineer, a written scope, and code in your environment. Same person from kickoff through go-live, and we stay on when production needs tuning.
Fit
Good fit. Bad fit.
Good fit
You know the task. Someone owns the edge cases
You can point at the work that eats hours every week. Someone on your team can say yes or no when the automation gets it wrong. You already run a CRM, inbox, or help desk. You just need the wiring.
- One process costing 10+ hours a week, with a number you can measure before and after
- Budget for one workflow, not another platform subscription
- Connect what you have. No rip-and-replace project
Bad fit
You want the dashboard before the process map
You want three named AI agents before anyone has mapped the work. Or you need a vendor who will execute the brief without pushing back. We are probably not the right call.
- Nobody owns it when automation fails overnight
- Personal data goes to an LLM with no legal basis written down
- Pilot budget, no plan to get to production sign-off
Where we start
Three jobs we do often.
02 · Handoffs
Approvals go to a person, not a Slack thread
Routing and sign-off with someone named when judgment matters. **Nothing launches without an owner for when it goes wrong.** If the model misses, one person gets pinged. Not the whole channel.
03 · CRM
Call notes hit CRM without someone retyping them
Summaries, action items, and pipeline updates land in the system your team already uses. We measure whether the data is right and the cycle gets faster. Not whether the demo got applause.
Live work
Clients we have shipped for.
Home Music Teachers
Lead handling across four countries
The bot handles intake. Your team only sees threads that pass the filter. One named engineer on the job throughout.
Wolves Summit
Inbound routing before a hard deadline
Startup conference site. Founder-facing traffic routed by intent. Fixed deadline, no scope creep.
Vegconomist
Publishing ops at daily volume
Multi-market media stack. Editorial output was outpacing what the team could coordinate by hand.
- −38% fewer support tickets after intake automation
- B2B client · 60 days after launch
- −70% less time on document handling
- Legal firm · 4-week build
- 4h back per day from manual CRM updates
- Series A SaaS · sync automation
What ships
What you get on paper.
Paper you can run against: specs, runbooks, signed process maps. Same engineer from kickoff through go-live, and we stay on after.
✓
Process map with names on who handles exceptions, signed before we build
✓
Written spec: which systems, which fields, what triggers what, what happens when it fails
✓
Tested on real data in staging before anything goes live
✓
Runbook for your ops team: what to do when automation breaks or confidence drops
✓
60-day report against the baseline we agreed at kickoff
✓
Monthly cost cap and off switch written down before go-live
Before you sign
Ask any vendor these first.
If they hedge on any of these, that tells you something.
1
Who gets paged when the model is wrong at 2am?
2
Where does personal data go before it hits an LLM, and on what legal basis?
3
What is the monthly cost cap, and what happens when you hit it?
4
Can we turn this off without breaking CRM or inbox sync?
5
Who is the named person from scope to go-live, not just the sales call?
FAQ
Three questions before you approve scope.
Do you sell AI agents?
No. We build workflows inside your stack. If you want a platform with three named agents and a subscription, we are the wrong fit.
Strategy or implementation?
Both. Same person. Whoever maps the process also ships the wiring. No handoff halfway through.
How do you measure success?
We agree the baseline before any code: hours per week, error rate, response time. We report against it 60 days after launch. If we cannot name the number, we do not take the build.
Where to go next
Related services.
Concrete solution
Bring the operational risk.You get a clear diagnosis and a concrete next step.
We are the right fit if you want a team that pushes back when it matters.
Reviewing first?
Company evidenceon the site.
Engagements with commercial outcomes on Work. Team bios and operating model on About. Nothing to download. Review it before you commit to a call. Open to review. Commit when ready.