Local AI Agents on Your Employees' Own AI Seats
A local AI agent lives in an employee's own Claude, Codex, or Copilot workspace and works on the files and systems that person can already reach, with no server to run. ITECS either coaches the employee through a Guided Build or builds the agent and hands it off.
- Who evaluates
- Department heads and the employees who will build
- Runs in
- The AI seat your employee already uses: Claude Cowork, Codex, or Copilot
- Connects to
- Files and systems that employee already has access to
- Typical first engagement
- A Guided Build Sprint or a Local Agent Sprint
Deployment patterns
Three ways to run an agent
Local AI Agents
- Where it runs
- The employee's own Claude, Codex, or Copilot seat. No server.
- Who evaluates it
- Department heads and the employees who will build
- What it connects to
- Files and systems that employee can already reach
- Typical first engagement
- A Guided Build Sprint or a Local Agent Sprint
- Where it runs
- A governed Linux environment ITECS operates, on frontier models
- Who evaluates it
- COO, CFO, and operations leadership, with IT reviewing
- What it connects to
- ERP, CRM, finance, and document systems through controlled integrations
- Typical first engagement
- An AI Blueprint, credited toward the build
- Where it runs
- A server with data-center class GPUs inside your network, on local models
- Who evaluates it
- CFO, CIO, IT director, and regulated buyers
- What it connects to
- The same systems, with the data staying on premises
- Typical first engagement
- An AI Blueprint and a sizing call for the server
Local AI Agents
What a local agent is
A local agent is built inside a seat you already license. It does the work of one person or one team, under that person's existing access.
- Where it runs
- In the employee's own Claude Cowork, Codex, or Copilot workspace. There is no server to host or patch.
- What it reads
- Only the files and systems that person already has access to. Platform subscriptions stay client-paid.
Delivery models
Two ways to build a local agent
- Guided Build
- The employee drives the build and ITECS architects and coaches, in 90-minute working sessions. It doubles as training and leaves an internal champion behind.
- Delivered Local Agent
- ITECS builds the agent in the client's workspace and hands it off with usage documentation and handoff sessions.
Continuity
Built to outlast the person who built it
- Archived
- Every guided or delivered build is archived in the ITECS client vault: workspace configuration, skills, prompt libraries, data-source maps, and usage documentation.
- Re-wired
- If the sponsoring employee leaves, ITECS re-wires the agent for a successor in typically one or two sessions, rather than rebuilding it.
- Cloned
- A proven agent can be cloned and adapted for other employees or departments.
- When it graduates
- When an agent needs server-side deployment, unattended scheduling, multi-user access, audit trails, or an SLA, it moves to a hosted agent. An AI Blueprint is then quoted, and guided or local build fees already paid credit toward it.
Pricing
What a local agent costs
Fixed-fee packages from the catalog. When an agent graduates to a hosted build, guided or local fees already paid credit toward the AI Blueprint.
- Guided BuildGuided Build Session90-minute working session$650
- Guided BuildGuided Build Sprint (4 sessions)One bounded agent or workflow · typically 2–3 weeks$2,400
- Guided BuildGuided Build Intensive (8 sessions)Complex multi-step agent$4,400
- DeliveredLocal Agent SprintOne workflow · 1–2 data sources$4,500–$9,500
- DeliveredDepartmental Local AgentMulti-step workflow · multiple sources and outputs$9,500–$18,000
- Data readinessData Readiness SprintOne department or use case$3,500–$8,500
Prices from the published AI pricing catalog. Sessions expire 90 days from purchase.
Example agents
Designs that suit Local AI Agents
Each is a starting design. An AI Blueprint adapts it to your goals and the systems it will connect to.
- Customer & SKU Profitability
Shows which customers, SKUs, plants, and programs create margin after cost, service, freight, and complexity.
- Manufacturing
- Finance
- Local AI Agents
- Hosted AI Agents
- Cash Flow Model Builder
Assembles comprehensive cash flow models from field exam output, historical financials, and prior reports.
- Financial Services
- Finance
- Local AI Agents
- Hosted AI Agents
- Back-Office Workflow Agents
Handles lead follow-up, invoice intake, and data entry inside the tools your team already uses.
- All industries
- Operations
- Local AI Agents
- Hosted AI Agents
- Company Knowledge Agent
Answers questions from approved company knowledge with citations, and keeps SOPs and runbooks current under human review.
- All industries
- Knowledge
- Local AI Agents
- Hosted AI Agents
- Private AI Servers
- Contract Clause Review Agent
Extracts key clauses from an inbound draft, applies the firm's or client's playbook positions, and proposes redlines with clause-level reasons the responsible attorney accepts or rejects.
- Legal
- Knowledge
- Private AI Servers
- Hosted AI Agents
- Local AI Agents
- CAS Month-End Close Agent
Works the firm's close checklist for each client accounting services client, surfaces uncategorized transactions, unreconciled items, and unusual variances, and drafts client questions and proposed entries for the accountant to approve.
- Accounting
- Finance
- Hosted AI Agents
- Local AI Agents
- Engagement Letter & Proposal Agent
Drafts the engagement letter and proposal from firm templates, carrying the firm's third-party disclosure language and any consent form counsel has approved, for the engagement partner to finish and sign.
- Accounting
- Sales
- Local AI Agents
- Hosted AI Agents
- Submittal & RFI Agent
Compares each submittal with the governing spec section, flags deviations for the PM or project engineer, and drafts RFIs with drawing and spec references.
- Construction
- Operations
- Local AI Agents
- Hosted AI Agents
- Bid Scope Review Agent
Reads the spec book, addenda, and bid forms to build a scope-gap matrix by trade, and flags terms such as pay-if-paid, notice periods, and liquidated damages for the estimator and counsel.
- Construction
- Sales
- Hosted AI Agents
- Local AI Agents
- Lease Obligation Agent
Abstracts primary terms, shut-in royalty, continuous development, Pugh, and depth clauses with citations, and calendars each obligation for landman approval.
- Oil and Gas
- Operations
- Hosted AI Agents
- Local AI Agents
FAQ
Local AI Agents FAQ
What is a local AI agent?
A local AI agent is a custom agent built inside an employee's own Claude Cowork, Codex, or Copilot workspace. It works on the files and systems that person already has access to, so there is no server to run.
Do we need new software or a server?
No server. The agent runs in AI seats you already license. Third-party platform subscriptions stay client-paid unless a proposal states pass-through billing.
What happens if the employee who built it leaves?
ITECS archives every guided or delivered agent in the client vault: workspace configuration, skills, prompt libraries, source maps, and usage documentation. ITECS re-wires it for a successor in typically one or two guided sessions rather than rebuilding it.
When does a local agent need to become a hosted agent?
When it needs server-side deployment, unattended scheduling, multi-user access, audit trails, or an SLA. An AI Blueprint is then quoted, and the guided or local build fees already paid credit toward it.
What if our files are not ready for an agent?
A Data Readiness Sprint inventories sources, reviews permissions, restructures folders, and cleans up metadata and naming before the build. Every build proposal either includes a data-readiness line item or confirms in writing that sources were verified build-ready.
Start with an AI Blueprint
The AI Blueprint reviews your workflow, data sources and integrations, specifies the architecture and the human-review model, and ends with a fixed-fee not-to-exceed for the build.