Dallas Crilley
In productionMeter CT19:27:01 Dallas, TX
Forward-Deployed Applied AI EngineerRevenue systemsPython + TypeScript

I work forward-deployed, turning revenue and operations workflows into production systems.

I sit with operators, map the fragile billing or data workflow, build into the CRM and systems already in place, and stay responsible after deployment. That has meant idempotent billing for an MSP, one connector contract across six vendors, and AI pipelines with measured gates and human control.
~19 monthsMeter running in an MSP’s billing stack
202 accounts · 931 work itemsone reconciliation audit, self-reported
6 integrations · one contractThroughline across six production vendors
CoHost AI Studio Stricter quality gate on CoHost transcripts
Throughline Retry-queue backoff in Throughline
public 27 extracts on GitHub
based Dallas–Fort Worth · CT · remote/DFW hybridSep 2026
Recommended route for hiring managers

One production system. One integration backbone. One applied-AI system.

Meter shows operator discovery through ongoing operations. Throughline shows the shared contract behind six integrations. CoHost shows measured AI gates before release.

Two skill stacks that don’t often overlap.

I keep walking into the same two conversations. The AI side needs someone who has already owned a CRM pipeline and billing reconciliation. The operations side needs evaluated AI with a review path and an operator who can stop it.

I sit between those lanes. Ten-plus years owning the systems that move work from a new lead to a paid invoice is the base layer: most recently as Head of Technology at Real News Public Relations, sole technical owner across six SaaS platforms and eight-plus production systems since 2018. Internal tools, applied AI, eval harnesses, and human review are the newer layer on top.

I learned this work inside my father’s company, where I was the only engineer. Head of Technology describes the function: I owned the systems, incidents, releases, and handoffs myself.

10+ yrs
Owning production systems across customer data, billing, reporting, and operations. Full history on hiring details.
3 systems
Featured on work, each written from the actual repository.
27 extracts
Public repositories you can clone tonight. The full list is on the proof ledger.

Selected systems

All case studies · Proof ledger
Meter Billing automation
Shipped
Intermedia usage, billed straight into ConnectWise. Moves Intermedia usage into ConnectWise invoices and removes the manual monthly reconciliation.
PythonConnectWiseIntermedia
~19 mo in production billing a real MSP
202 accounts in one audit incident (self-reported)
Read the case study
CoHost AI Studio AI automation
In progress
Nothing publishes until it clears the gate. Checks audio, video, and transcripts before an episode goes live, and holds anything that misses the bar.
PythonTypeScripteval harnesshuman-in-the-loop
20+ pipeline steps
11 quality metrics
Read the case study
Throughline GTM systems
Shipped
One connector interface, every system in sync. Keeps six vendor tools in sync and puts each client’s information in one reliable place for operations and reporting.
PythonPostgreSQLOAuth 2.0retry queues
Read the case study

The same studio also runs the live TV production automation I built: the operator stays on the live decision.

Public code

Proof ledger · GitHub

Start with the connector contract behind production integrations, then inspect the delivery and human-review boundaries. The rest stays in the proof ledger.

27 public extracts on the proof ledger

Throughline Connector Kit

The sanitized public kit behind Throughline: one four-method connector contract, the sync engine, sample CRM data, and tests.

Shipwright

Cold-clone reviewed

An agent that takes an approved GitHub issue and returns a tested, reviewable pull request.

Continue for more context Architecture writing and how I work

Architecture writing

All posts
Adapting Cloudflare’s $1 Review Factory for RevOpsAgent systems · RevOps architecture
Cloudflare’s code-review factory, adapted to revenue data: coordinator, specialist fusion, risk-scaled compute, and the resilience work needed to make it usable as a demo. Read the article ~7 min read
The Four-Method Connector Contract, and Knowing When to StopThroughline · Connector design
A four-method connector contract that keeps six vendor integrations behind one engine-owned sync boundary, plus the restraint it took to keep the interface small. Read the article ~10 min read

How I work

What I own
The layer between AI and day-to-day operations: customer data, billing, reporting, internal tools, quality gates an AI output must clear before it ships, and the workflow logic operators actually depend on.
What I optimize for
Small surface, strong contracts, practical automation, and a clean handoff to the people who run the process after the engineering work ships.
Where I am strongest
When a process is manual, fragile, or hard to trust; when the data crosses systems that disagree; or when an AI workflow needs a quality bar, a review layer, and an operational owner.
Where I am not the right fit
Pure ML research, ground-up platform infrastructure, Kubernetes platform work, or roles that also require me to own visual design. I work at intermediate level on AWS and Google Cloud and ship with Docker, CI/CD, and managed platforms; I am not the person to build your cluster. I will tell you when a role is a stretch rather than overstate the fit.

Hiring for this kind of work?

Always glad to compare notes with people building applied-AI workflows, internal tools, and the business systems they run on. If you’re hiring for that work, email me. I read everything and reply within a day.

Senior IC · Dallas–Fort Worth · remote preferred or DFW hybrid

More ways to reach me
[email protected] copy LinkedIn GitHub