Forward Deployed Engineer, live answer, requirement 12 of 12

Client-facing delivery

I turn engineering work into updates that client architects, security leads and business owners can each act on.

Built by Gus Assuncao of Gus IT LLC for a Forward Deployed Engineer application. Luca is the AI platform Gus IT builds and operates.

Try it

Paste rough engineering notes. The demo finds the jargon first, then writes a sponsor update that avoids it, keeps the status faithful to the notes, and flags any term that slips through.

Public demo on Cloudflare Workers AI. Inputs are screened by Llama Guard 3 before any other model runs, requests are rate limited, and nothing here connects to a Luca or customer system.

The requirementWork with client teams, architects, security, infrastructure and engineering staff, and communicate with each in their own terms.

How it works

Map the stakeholdersI record every client architect, security owner and infrastructure lead as a contact in the workspace CRM. I tag each contact with the decision that person owns, so every update has a named reader.
Index their languageI upload their runbooks, architecture notes and policies to a separate knowledge store in the retrieval service. The service checks the caller's access to that store before it searches. That lets me write with the system names their teams already use.
Flag the jargonBefore I draft, I list the terms in the engineering notes that a business owner would not know. KEDA and CloudNativePG are typical, and each term gets a plain description of what it does.
Draft and checkI draft through the multi-provider model gateway, which holds the provider keys and logs the provider and model for each call. The draft must avoid the flagged terms, keep the status true to the notes, and claim no result the notes do not state. The demo on this page automates the term list, the draft and the term check on Cloudflare, with Llama models on Workers AI. It does not call the Luca platform.

Tools

Tool	What it does here	Status
Multi-provider model gatewayAvailable	Carries my drafting calls, holds the provider keys, and logs the provider and model for each call.	Available
Document retrieval serviceAvailable	Stores the client's runbooks and notes, and checks the caller's access to that store before it searches.	Available
Workspace CRM and calendarAvailable	The CRM holds the tagged stakeholder contacts and the logged updates, and the calendar holds each review.	Available
Approval gates and auditEarly access	Hold an agent's destructive tool calls until a person approves or denies them, and record each decision.	Early access
Cloudflare Workers AIDemo only	Runs the Llama models behind this page's jargon list and draft, with Llama Guard 3 screening input first. It is a public demo environment, not a customer deployment.	Demo only

Available means shipped and in use. Early access means built but not generally available. Roadmap means designed, not built. Demo only means it powers the public demo, not customer deployments.

The write-up has every step of how I deliver this at a customer, with the tools and their status.

Read the write-up on gusit.de

The other answers

LLM applications in productionOn Luca, model calls normally go through a gateway that holds provider keys, records each chat call and sets a model per task.Prompt engineeringI write the output shape first, measure the prompt against each model's context window, and check replies against that shape.Retrieval-augmented generationChat answers over a customer's own documents, returned with the matched document names, after a check that the caller may use that persona.AI agents and orchestrationI build agents that call your systems through registered tools, still in early access, and workflows that start on business events.Request classification and routingI build automation that classifies each inbound request, plans bounded tasks, and holds high-risk tasks for approval; the dispatcher is in early access.AI workflow orchestrationI map the steps, API contracts, and data flows between a customer's systems and the models before I build the workflow.API and integration designI publish the API contract first, gate it with keys and scopes, then build integrations against it.Hybrid enterprise integrationI connect AI services to your identity, applications and data, and run the platform on Kubernetes on Azure Local.Prototype to productionI take a prototype through generated tests and a two-approval merge gate to a production deploy that rolls back if the new pod keeps crashing or cannot start.Approvals and exception handlingIn chat, I hold each Gatekeeper tool marked destructive until the signed-in user approves it, with expiry and a record. This path is in early access.Evals and output validationI built a versioned rubric judge for a tutoring app, and I trace failed or slow model calls to their provider.

Built by Gus Assuncao of Gus IT LLC for a Forward Deployed Engineer application. Luca is the AI platform Gus IT builds and operates. Contact gus@gusit.de. Claude is a product of Anthropic PBC. Cloudflare and Workers AI are trademarks of Cloudflare, Inc. Llama is a trademark of Meta Platforms, Inc. Other names are trademarks of their respective owners. Gus IT LLC is an independent engineering firm and is not affiliated with or endorsed by these companies.