Telecom sales, minus the busywork.
I help telecom sales teams accomplish more by automating the repetitive work, from prospecting and discovery through solution design, quoting, deployment and post-sale reconciliation.
One live system cut detailed quote drafting from about an hour to five minutes. See the case study
I lead a telecom sales team and build the tools it uses every day.
AI handles ambiguity. Software handles rules. People own consequential decisions.
Start with a Scoping & Data-Fit Assessment → one workflow, $2,500–$5,000, credited in full to your build if it's signed within 60 days of the assessment readout. See services & pricing
Measured per workflow on shipped systems, as of July 2026 — sources, methods, and limits are in each case study. Results, not guarantees.
Clarity, turned into software that runs.
PD Insights builds internal AI systems for the workflows where a wrong answer costs money — quoting, lifecycle decisions, research, and revenue ops.
I'm a revenue operator who also writes the Python, designs the schema, and gates the deploys — so the AI is pointed at pipeline, margin, and risk, not novelty.
Six systems I'm asked to build most
Each is delivered as working software — scoped, built, measured, and handed over with the tests that prove it.
Agentic workflows
Turn calls, voice memos, and unstructured input into committed, structured records — with rep-approval gates, not blind automation.
Knowledge systems (RAG)
Source-of-truth retrieval that stops the same question being asked forty times. Answers are designed to cite source material; unsupported gaps are disclosed instead of filled in.
Sales-cycle compression
Intake-to-quote workflows for complex catalogs — deterministic pricing, review flags, internal economics suppressed. Days of back-and-forth become a same-day answer.
Lifecycle & EOL planning
Inventories turned into prioritized replacement pipelines — surfacing end-of-life risk before revenue walks out the door.
Revenue & outbound automation
Find, enrich, sequence, and report on target accounts at scale — CRM and Microsoft 365 wired in, admin handed to background agents.
Local & private deployment
On-prem-capable models tuned for latency and cost, so when required, sensitive legal, financial, and customer data can stay inside your environment.
Case studies
Three flagship builds, each with a full written case study. Metrics are drawn from the linked case studies and should be read with the limits noted in each one.
Quote Bot Hardening
Took a local-first Zulip quoting assistant from an initial code audit to a tested, eval-gated tool — reproducible builds, deterministic quote math, and a human-review gate, with the model structurally unable to invent a price.
"Pete got fast models running on our own hardware that are private enough for our most sensitive data — we're not sending anything to the cloud anymore."
— Jeff D. · Independent Telecom Consultant
Router Lifecycle Knowledgebase
Turns a twelve-tab device workbook into cited, end-of-life replacement answers in seconds — across 1,024 current and EOL devices, with source citations and visible coverage gaps.
"Instead of digging through a twelve-tab spreadsheet, my team asks one question and gets a cited answer on what's end-of-life and what replaces it. It's the first thing they open now."
— Ken A. · Client Partner, national wireless carrier
Pricing & Quote Intelligence
A unified pricing and deal-intelligence engine — 4,500+ SKUs across 7 vendors compiled into one deterministic catalog that flags end-of-life hardware and surfaces real deal economics before a quote goes out.
"Quote prep went from a couple of hours to under ten minutes — and it catches discontinued hardware before it ever reaches a customer."
— Corey H., Sales Engineering Lead · Wireless solutions partnerNine more systems, including the POTS agentic workflow, One Talk call-flow designer, and cellular site survey. Four of them have full write-ups.
See all case studies →Have one messy workflow worth fixing?
Bring the workflow, the data sources, and the failure modes. I'll help map what can be automated safely and what should stay human-reviewed.
Start the 2-minute fit check →Assess → Build → Run
A repeatable path from "we have a messy workflow" to "it runs in production and we can prove it."
Assess
Map the workflow, source quality, and handoffs; find where time, margin, and risk leak; pick the one worth shipping first.
Build
Data contracts, safety boundaries, and test-first implementation with evals, review points, and acceptance examples.
Run
Keep sources, rules, and model behavior current under a defined care agreement, with a managed change queue.
Start with the right level of work
Start with one assessment: Scoping for one workflow, or the Audit for several. It's scoped separately from the build; the fit call is free. AI Team Training ($5,000–$15,000) is available at any stage. Planning ranges in USD, confirmed in a written proposal.
Scoping & Data-Fit Assessment
Confirm the sources, rules, and data fit for one workflow. Credited in full to your build if it's signed within 60 days of the assessment readout.
AI Workflow & Operations Audit
Inventory AI use, map manual work, set time and error baselines, and leave with a ranked build / no-build roadmap.
Focused build
Knowledge & pricing, quoting, revenue workflows, or commission & billing assurance — one scoped system with tests and review gates.
Managed System Care
Source refreshes, checks, model and tool updates, and a managed change queue.
AI that can show its work
Every PD Insights system is built around approved data, clear tool boundaries, cited sources, exact calculations where math matters, test cases, logs, and named human approval before high-impact, AI-drafted output leaves the workflow.
Approved data
What data may enter the workflow, which tool and account may handle it, and what must be redacted or excluded — decided up front.
Cited answers
Facts and recommendations point back to approved sources. Unsupported claims are flagged or refused, not filled in.
Human approval
AI-drafted quotes, external messages, pricing changes, and legal language stop for a named reviewer before they leave the workflow.
Tests & records
Known cases, failure cases, logs, and review decisions create evidence that the workflow behaves as intended.
Client separation. PD Insights keeps client environments, client-specific code, source data, credentials, and commercial information segregated and does not share them between clients. Ownership and any case-study disclosure are agreed in writing.
PD Insights provides operating, workflow, and technical controls — not legal advice, a formal audit, or certification. Regulated or high-risk uses should be reviewed by qualified legal, privacy, and security professionals.
How it ships
Your cloud, a PD Insights–managed cloud, or local models — tested, documented, and integrated with the systems you already run. Here's the toolchain behind it.
Where it runs
How it integrates
How it's handed over
Tools under the hood: Claude · GPT · OpenAI Agents SDK · Hugging Face · Ollama · Python · FastAPI · React · Neon Postgres · Chroma · eval harnesses · CI/CD.
A revenue operator who can also build the machine.
For 20+ years I've worked in telecom and IoT channel sales. I built the Wyless Connect business unit from $0 to $10M in annual revenue, built router and wireless revenue lines from near zero to multi-million-dollar scale at ORBCOMM and CTS Mobility — where I helped move fixed wireless from roughly 5% to 80% of activations — and co-founded and sold Venture Mobile.
Through PD Insights, I specialize in AI workflow automation for U.S. telecom channel partners that quote multi-vendor hardware and carrier services. I help their sales teams accomplish more with less repetitive work, from prospecting through post-sale reconciliation. I also lead a telecom sales team and build the tools it uses every day, so I can shape the plan, open the door, win the business, and build the machine behind it.
MS, Engineering Management
Quick fit check
Tell me about the workflow. If it's a fit, we book a 30-minute fit call from here — if it's not, I'll tell you honestly what to fix first. One boundary: design and build work starts after a paid Assessment or Audit, not on the call.
Prefer to talk first? Book a 30-min fit call →
Let's map one high-value workflow.
If you've got a messy, manual process that should be running as software, that's exactly the kind of thing I turn into clarity. Book a 30-min fit call — no deck required.