# AI agents and automation that show their work. > AI agents, retrieval with citations, document extraction and workflow automation, built with an evaluation set and a review gate where errors cost money. Page: https://adjltechnology.com/services/ai-engineering/ Updated: 2026-11-12 AI Engineering We build AI systems that do one job inside a business that already runs. Agents that call your tools. Retrieval that cites its sources. Extraction from records nobody structured, and drafting that stops at a review gate. Each one ships with an evaluation set, so you can tell whether it’s still right next month. [Watch a run stop](https://adjltechnology.com/services/ai-engineering/#replay) [Talk to Daniel](https://adjltechnology.com/services/ai-engineering/#contact) - **Inputs:** Your documents, records and tools - **Builds:** Agents, retrieval, extraction, routing, drafting - **Measures:** An evaluation set of real cases, plus a trace of every run - **Hands over:** Code, prompts, evals and docs, in your repository People read the top layer, crawlers follow the middle one and machines parse the bottom one. What it covers ## Narrow systems, measured from day one. ### Agents that call tools An agent is a loop. It plans, calls a tool, reads the result and decides what’s next. We give it narrow tools, a budget and a log of every call. It stops and asks when the evidence runs out. ### Retrieval with citations Answers come from your own documents, and every answer links to the passage it came from. A wrong answer traces back to a wrong document, which someone can fix without retraining anything. ### Extraction Fields pulled out of invoices, contracts, filings and emails nobody structured. Each field is checked against a schema. Anything missing goes to a person instead of getting filled in with a guess. ### Routing and drafting Classify what came in, send it to the right queue and draft the reply. Drafts wait for a person wherever a wrong one would cost real money. ### Evaluation Before launch, a set of real cases with known right answers. After launch, the same set runs on every change. You find out a model update made things worse before your customers do. ### Handover The code, the prompts, the evaluation set and a runbook go into your repository. Swap the model out in a year and the scaffolding is what you keep. Try to break it ## Retrieval you can argue with. The same retrieval pattern as the home page, with the controls exposed. Move the confidence floor and watch the gate change its mind. Then try a question this site can’t answer. 1. [Who owns the code when you’re done?](https://adjltechnology.com/services/ai-engineering/#ask-q1) 2. [Do you sell a chatbot subscription?](https://adjltechnology.com/services/ai-engineering/#ask-q2) 3. [Who ownes the code?](https://adjltechnology.com/services/ai-engineering/#ask-q3) 4. [Do you build iOS apps, and who owns the code?](https://adjltechnology.com/services/ai-engineering/#ask-q4) A system we run ## A pipeline that stops and asks a person. This is the underwriting engine we run for ADJL Capital, replayed stage by stage. A model writes the narrative at the end and nothing else. It’s handed figures that are already computed, and its prose is never parsed back into a number. Pick a bad input and watch where the run stops. - Not one property. Nothing was fetched and nothing was spent. - The provider had nothing on this listing. The fields are left blank for a person to fill in, and no figure is guessed. - Held at the price check. The analysis doesn’t run on a price nobody confirmed. - No local water schedule on file. The line uses the national average and says so. Review gates ## Where a person stays in the loop. We put a review gate wherever a wrong answer costs real money. We keep them few, because a person who approves everything soon stops reading. Choosing where they go is part of the scope we write. Proof ## Where this already runs. The patterns on this page run in systems we operate. Each page below shows one of them stage by stage. - [How an AI rollout runs](https://adjltechnology.com/work/ai-implementation/) - [A model that writes prose, never figures](https://adjltechnology.com/work/real-estate-intelligence/) - [An options model checked against real quotes](https://adjltechnology.com/work/trading-infrastructure/#research) Fair questions ## Questions about AI builds. ### Which models do you use? Whichever fits the job and your data rules. We work with Claude, OpenAI models and open-weight models run locally. The evaluation set makes the choice, and it lets you switch later without guessing. ### Can it run without sending our data to a model provider? Often, yes. Retrieval and extraction can run on a local open-weight model inside your environment. Where a hosted model is the better tool, you’re told what leaves, where it goes and how long it’s kept, before anything is built. ### How do you know it works? An evaluation set of real cases, written before the build and scored on every change. Plus a trace of every run, so a bad answer can be followed back to the step that produced it. Start here ## Tell us what’s slow, or what can’t be found. One paragraph is plenty. Tell us what you want built, the step that costs the most, or the page that should rank and doesn’t. If you know why the obvious fix hasn’t worked, say that too. [Start a project](https://adjltechnology.com/start/) [daniel@adjlcapital.com](mailto:daniel@adjlcapital.com) [Email Daniel](mailto:daniel@adjlcapital.com) Daniel reads and answers these himself, usually within a day or two. No sequence, no drip, and nothing sold to anyone. [ADJL Technology](https://adjltechnology.com/) Today’s investment, tomorrow’s legacy. ADJL Technology builds AI systems, websites and apps, and the technical SEO that gets them found. Founded and led by Daniel Laskowski. [daniel@adjlcapital.com](mailto:daniel@adjlcapital.com) Built 2026-11-12 from commit 6afca01. No cookies, no trackers, no third-party scripts. ADJL Technology. Nothing on this site is an offer to sell or a solicitation of any security, and nothing here is investment advice. Descriptions of internal systems are general by design and omit parameters and thresholds.