Forward Deployed Engineering

MeetCarbon delivery method · AI forward deploy

General-purpose AI lowered the bar for “talking”
FDE sets the bar for “shipping

FDE covers classic on-site system delivery. The core job is putting large models in the customer environment, wiring real data and permissions, and standing up business Agents so the front line actually owns usable AI — more than another public-web chat window.

Model deployAgent go-liveIn-system embedOn-site closed loop
Scroll for the full method
Product feedback
Field → Platform
Adoption
Field Signal
ON SITE
  • ScenesOffices · parks · stations
  • AIPrivate models · Agent · RAG
  • ConstraintsGov network · unified identity · data stays in-domain
  • GoalInstall in the stack · use daily · own the capability

Deployment readiness · live loop

The Problems We Sit Inside

FDE sits inside the problems that actually stop the front line

Classic delivery makes the system usable. AI forward deploy also makes the model installable, the Agent wired, and the capability stay behind. Those issues rarely show in a demo; they surface on the customer intranet.

Deploy

The model only chats in a public-web demo — how do you actually run inference on the customer intranet, government network, or a private stack?

01
Use

You wired a large model and it answers the wrong question or overreaches — how do permissions, data definitions and platform capabilities stay homologous with the conversation?

02
Agent

Customers want energy-carbon weeklys, exception judgment and work assistance — how does the Agent sit inside the existing workbench?

03
Own

When the vendor leaves, prompts, knowledge bases and skill graphs leave too — how does the customer actually own operable AI?

04
Not Consulting. Not Pure Product.

Three delivery modes — how close they sit to the problem

The industry is not short of model APIs or implementation manuals. It is short of engineering that installs AI in the customer’s own stack and grinds it until it works on site.

Pure product, remote

One capability, many customers

  • HQ iterates from requirement docs
  • AI stays in the public demo environment
  • After go-live you queue on tickets
  • A smooth demo ≠ front-line adoption

Classic implementation / consulting

Can configure and present; hard to change the product

  • Click the config sheet and leave
  • “Wired” is not the same as “usable”
  • Agents struggle to embed in business systems
  • Field learning rarely flows back to the platform
MeetCarbon

MeetCarbon FDE

One customer, many capabilities

  • People sit in the real environment and intranet
  • Deploy the model + build the Agent + wire permissions
  • AI embeds in the workbench and daily workflows
  • Capability can be handed over, operated and retained

Classic on-site system delivery still matters. FDE’s other core is “AI forward deploy” — putting large-model capability directly into the user’s internal systems, so users do not live forever on an external general-purpose assistant.

What FDE Means Here

What MeetCarbon FDE is

Forward Deployed Engineer·Frontline deployed engineer

For MeetCarbon, FDE is both a role and a delivery promise: enter the customer’s real environment, make the business system daily work; and put large models, Agents and platform capabilities inside a boundary the customer controls, so AI becomes the organization’s own productivity — more than a one-off demo.

Software can be delivered remotely. Usable AI has to grow inside the customer’s systems.
01

People follow the project

Machine rooms, wards, duty rooms, the customer intranet — the workbench moves to where the problem happens.

AI integration also has to finish on the real network and permissions. A public sandbox that “looks chatty” is not enough.

02

Problems come from the front line

See how tickets are dispatched, how assessments are filed, how materials are submitted — then decide how the system and Agent grow.

The Agent skill list comes from front-line tasks, from the model vendor’s capability poster last.

03

AI installs into internal systems

Deploy inference, wire data and permissions, orchestrate Agents, embed in the workbench and business flows.

The goal is sustainable runtime in the customer environment — more than another external chat link.

04

Field learning feeds the product

Shared pains from offices, parks and campuses harden into MeetCarbon defaults and Atan skills.

The field is a gravel road; the platform is the paved highway. FDE turns the former into the latter.

AI Forward Deployed

FDE’s other core: put large models in the customer’s internal stack

Everyone can use a general-purpose large model. That does not mean the customer organization “owns” AI. MeetCarbon FDE finishes four jobs on site — deploy, use, build Agents, internalize capability — so Atan and MeetCarbon OS actually enter an environment the customer can control, operate and hold accountable.

AI does not replace statutory accounting, audit or engineering decisions. FDE turns “can talk” into “helps real work inside permission and data boundaries”.

01

How we deploy large models

Run inference inside a boundary the customer can accept

Choose public-cloud API, dedicated cloud or private inference from the customer’s security and network conditions. Finish gateway, GPU/compute, image and model-routing setup, intranet reachability and monitoring — do not hand keys to business users and say “call the API yourselves”.

  • 01Assess: can data leave the domain, government/intranet isolation, latency and concurrency
  • 02Land: inference / gateway / model routing into the customer environment or a dedicated channel
  • 03Operate: health checks, rate limits and fallback, keys and audit trails
  • 04Accept: real Q&A and timeout pressure tests inside the customer network
Gravel Road → Paved Highway

The field is the entry for product and Agent evolution

A good FDE model does not forever custom-build for one person. It hardens real constraints and high-frequency tasks found on site into platform defaults and Atan skills — so the next customer walks fewer detours.

01

Embed on site

Hear the business and network/security constraints; choose the model-deploy shape

02

Install in the stack

Inference reachable, permissions homologous, Agent in the workbench

03

Use in daily work

Train for adoption until the front line is willing to ask and to use

04

Feed the product

Shared skills enter the roadmap and reuse at scale

How We Operate

Four-step method: ship the system + install the AI

01

Hear the real need

Clarify business blockers and AI tasks together

The kickoff says “integrated control” and “add AI”. What actually shapes the product is the approval chain, assessment methodology, and what the front line asks and completes every day. System modules and Agent skills grow from there.

Who approvesWho closesHigh-frequency Q&AAgent tasks
02

Get it right inside constraints

Design the system go-live path and the model-deploy path together

Unified identity, government network, masking and audit, security tests, and “can data leave the domain” all go in. First walk a path that can go live and an inference path that can be private or dedicated, then polish experience.

Unified identityIntranet reachabilityModel routingAudit trail
03

Close into one entry

Business portal and Atan share one org-permission set

Integration starts with one entry, one org, one accountability. Colleagues open one workbench to do facilities and energy-carbon work, and to ask Atan — answer permissions and page permissions stay homologous.

Unified portalAtan entryHomologous permissionsMaterials can be filed
04

Stay after go-live

Follow system adoption and Agent ops together

The day the system runs and the model is wired is when real use begins. Whether rules need tuning, knowledge needs filling, which skills nobody uses — they become iterable versions, plus a capability handoff.

Adoption follow-upSkill iterationKnowledge updatesHandoff pack

Go-live is the start. Delivery is when the front line actually uses the AI.

A Week on Deployment

A week on site looks roughly like this

Days are not identical. A week mixes classic integration and process polish with live iteration on model routing, Agent skills and knowledge. The bar stays: smoother site, stabler acceptance, AI that actually helps.

01
Mon
驻场节奏 · 1/4

Align blockers and AI tasks

Align business blockers and this week’s AI goals: which Q&A / work paths must run first, and what still blocks model deploy and permissions.

Blocker listAgent priorityDeploy blockers
Who Thrives Here

We hire people who close the loop on site

FDE stands between R&D, implementation and AI go-live. You do not need to do everything. What matters is willingness to be there, to talk, and to close models and Agents into the customer’s systems.

Willing to be there

Accept residency, intranet integration, training and acceptance — work is not always at a desk.

Can talk

Ask about business methodology, and whether data can leave the domain and who may see the answer.

Can close the loop

From deploying the model to building the Agent, to front-line use, to a handoff the customer can run.

See the FDE role and apply
Background → What you ship
Different origins, one forward-deploy path
From
Backend / full-stack / frontend
To
Write field constraints and model access into shippable designs and code
From
Implementation / delivery / ops
To
Grow from “finished the config” to “can change the product and install AI”
From
LLM / Agent engineering
To
Grow from demo chat to a business Agent operable on the intranet
From
Pre-sales / solutions
To
Grow from “can explain” to “can stay, land and hand off”
Field Note · Wuchang

Field note: Wuchang smart facilities

Serving the Wuchang District Government Offices Affairs Center and advancing the “Wuchang District Smart Facilities Integrated Control Center”, engineers sat as close to the business as possible — first pulling fragmented, urgent, hard work into one entry. AI grew on the same org and permission system, without a second stack.

Repairs and property

Before

Phone, WeChat and verbal handoffs mixed; dispatch was slow, progress invisible

After FDE

Pulled into one ticket stack with SLA; staff can see progress

Meetings and visitors

Before

Rooms booked solid and empty at once; the gate stalled between wait and security

After FDE

Rules were ground into booking and access on site, not left on a blueprint

EV charging and energy-carbon

Before

Order, fairness and abatement scoring stacked; materials were hard to file

After FDE

One entry, data methodology that can roll up, filings that land when it counts

Government hard constraints

Before

Unified identity, government network and security tests were “after go-live”

After FDE

Constraints entered integration from day one; AI obeys the same identity and boundary

The above is project-progress language. It is not an official endorsement or administrative evaluation.

Platform × Field

Atan and the OS are the capability surface; FDE is the delivery surface that installs them on site

Atan is the unified agent entry and persona. MeetCarbon OS / AI Runtime provides configurable models, Agent orchestration and homologous permissions. FDE installs all of it in the customer environment and grinds it until daily work.

Atan does not replace statutory accounting, audit or engineering decisions. FDE does not replace the customer’s business accountability. We deliver AI capability that can run, be operated and be handed over.

Next Step

Make zero-carbon ship, and install AI on site

For institutions: you need engineering that can reside, deliver the system, and put large models and Agents in the internal environment. For talent: you want to make AI daily work at the customer site, more than closing a ticket.