A field guide to work with agents.
Explore practical guides, product workflows and technical documentation. Find the next useful step, from a question to an evidence-backed result.
What this library holds
Every public page GoCux publishes is collected here: product surfaces, worked examples by domain, connection notes, long-form articles, release notes and the complete technical documentation. One catalog covers all of it, so a question can be answered without first guessing which section owns it.
The sections
- Documentation — the workflow and endpoint contracts: inputs, permissions, outputs, failure states and migration notes.
- Products — the workspace surfaces themselves, and what each one is for.
- Use cases — the same surfaces arranged around a kind of work, from research to document review.
- Integrations — what connecting an external system involves, and where the permission boundary sits.
- Articles — concept and method guides for agents, retrieval, extraction and monitoring.
- Journal — short notes on approvals, evidence, monitoring and memory in agent work.
- Learn — short explanations of the terms the rest of the library assumes.
- Comparisons — how to run your own comparison, and what to record while you do.
Finding the next useful page
- Search for the noun you actually have — a document, a monitor, a dataset, an approval — rather than the name of a feature you are guessing at.
- Narrow by section when the result list mixes concepts with reference material. Documentation answers how a contract behaves; articles answer why you would use it.
- Open one page and read its related links before widening the search. Sections connect where the work connects, and the neighbouring page is usually the one you wanted.
What to expect
Articles, journal notes and learning pages are written in English and Turkish. Where a page names another company's product, it describes what kind of tool it is and what to check, not a GoCux measurement of it.
286 resources
- Journal
A ceiling for agent spend: caps, bounds and one stop control
How to keep agent work from consuming more than you meant: visible credits, a daily cap that really stops, bounded tasks and one control that halts everything.
governance - Articles
A competitive intelligence pipeline where every claim has a source
Run competitive intelligence with agents: questions first, sources mapped to them, a cadence per signal, evidence on every claim and review before anything is shared.
research - Articles
A deep competitor analysis an agent can run and you can verify
Plan a one-off competitor analysis an agent can execute: a decision to inform, approved sources, a comparison table with evidence per cell and honest open questions.
research - Journal
A footnote is not a source: making agent findings checkable
How to tie each finding to the exact passage that supports it, why a link or a tidy footnote proves nothing by itself, and how reviewers should check support.
research - Articles
A LangChain search tool with citations, injection guards and tests
How to define a search tool for a LangChain agent, shape results for the model, keep citations verifiable, defend against injected pages and test the wiring.
research - Articles
A repeatable deal sourcing workflow: criteria, evidence, review
How to build a repeatable sourcing workflow for acquisition or investment targets: written criteria, evidence for every candidate, human review before outreach.
research - Company
About GoCux
GoCux brings conversations, project knowledge, research and reviewable work into one workspace. Explore a question, follow a task and turn the result into something useful.
- Documentation
Adapt a coding-agent client
Connect a local coding workflow while retaining local execution responsibility.
integrations - Documentation
Add supported fields to a collection
Expand a reviewed record with evidence-backed attributes.
findall api - Articles
Agent-built market research reports that survive review
Framing the question, approving sources, structuring the report and checking evidence before an agent-built market report or intelligence feed is shared.
artifact - Learn
Agentic search: an agent that plans, reads, refines and cites
How agentic search differs from one-shot search, what the plan, read and refine loop looks like, where it goes wrong, and what a team should control.
research - Learn
Agentic workflows versus fixed automation, and where people decide
What makes a workflow agentic, how it differs from scripted automation, and where human decisions belong so the agent can move without anyone losing control.
research - Articles
AI agents, defined: goal, tools, loop and memory
A working definition of an AI agent built on goal, tools, loop and memory, how it differs from chatbots and workflows, and what makes it safe to delegate to.
research - Integrations
An external AI gateway: integration design guide
Plan a dependable route from an assistant request to a model response. Decide how usage, delays and unavailable services will appear to the person doing the work.
- Integrations
Anthropic: integration design guide
Plan an assistant workflow around Anthropic messages and tools. Decide what context to share, which actions need review and how to check the result.
- Journal
Approve the sources before the research starts
Why a research plan should name its allowed sources, why an empty list must mean no source at all, and what to do when the material you need is not on it.
research - Journal
Ask first, act second: the case for an approval gate
What goes wrong when agents act without a pause, what a good approval gate shows the person deciding, and why a single click is enough when the gate does its job.
governance - Integrations
AWS Marketplace: integration design guide
Plan how a service purchased through AWS Marketplace fits into your work. Identify the account, subscription and information the workflow needs.
- Documentation
Bring existing evidence into a task
Prepare authorized documents as reusable project context.
task api - Learn
Browser agents: what they can do and where a person stays involved
What a browser agent is, the jobs it suits, the risks that come with logins and live-site actions, and how to supervise one with approvals and a visible trail.
browser - Documentation
Budget evidence-collection work
Estimate work from the actual GoCux operations in a collection workflow.
findall api - Documentation
Build a conversational research response
Combine the supported chat surface with explicit evidence workflows.
responses api - Documentation
Build an evidence-backed collection
Organize a set of entities or records supported by project documents.
findall api - Products
Build answers around context and review
Bring your question and supporting context together. Choose a conversation, a research finding or a structured output, then review how well it answers your request.
chat - Articles
Build or buy a research agent: a decision guide for team leads
How to choose between building a web research agent and buying a deep research API: control, evidence, upkeep, cost model and governance, plus a checklist.
research - Articles
Building a market map an agent can defend and keep current
Define the category, turn it into criteria an agent can test, collect candidates with evidence, report coverage honestly and keep the map current as markets move.
research - Articles
Chatbots that stay current: retrieval, freshness and when to refuse
How to design a chatbot or assistant that answers from current sources: the retrieval step, freshness rules, real-time data tools, citations and when to refuse.
chat - Documentation
Choose a developer integration path
Start with the smallest integration that preserves GoCux authority.
integrations - Documentation
Choose a GoCux workflow
Match a client integration to the supported GoCux operation before writing the adapter.
getting started - Documentation
Choose chat or durable execution
Select the GoCux execution surface instead of importing another service’s processor names.
task api - Articles
Choosing a deep research API: depth, speed, cost and citations
How to choose a deep research API: depth, speed and cost trade-offs, report structure, citation quality, faster modes, and an evaluation you run on your own questions.
research - Articles
Choosing a personal AI agent you can trust with real access
What to compare across self-hosted and hosted personal agents, how they tend to fail, and the scoping, approval and logging habits that keep them dependable.
cli - Articles
Choosing a search tool your agent can actually work with
What an agent needs from search: machine-readable results, passages, citations, freshness and tool-calling fit, plus a checklist for comparing options on your tasks.
research - Articles
Command-line interfaces, and why agents are so good at them
What a command-line interface is, why text-in, text-out tools suit AI agents so well, and the guardrails to set before an agent runs commands for you.
cli - Documentation
Common GoCux workflow questions
Resolve common differences between chat, research, tasks and retained context.
resources - Articles
Company and industry news alerts that stay worth opening
How to write news alert rules for single companies and whole industries, collapse duplicate stories, define materiality and choose between digests and real-time.
monitor - Articles
Company research data: registries, filings, news and vendors compared
A selection guide to company research data: registries, websites, news, filings and vendors, weighed by coverage, freshness and provenance, with a checklist.
research - Comparisons
Compare search backends by the task they support
Choose a search backend around the result you need: useful links, source passages or a research answer. Build a comparison that tests each part of that journey.
- Documentation
Connect a local agent extension
Let a local extension own its tool and permission loop.
integrations - Documentation
Connect MCP tools to a task workflow
Choose between a local invocation and a governed durable task.
integrations - Documentation
Continue a task with context
Carry useful context between conversations and durable work without inventing shared state.
task api - Documentation
Control document import inputs
Use explicit file metadata and classification to make imports predictable.
extract - Documentation
Control which sources support research
Fix evidence scope at review time and keep provenance visible.
resources - Products
Conversations that lead to useful work
Bring a question and the context that matters. Explore an answer in conversation, then choose the next step with a clear outcome in mind.
chat - Documentation
Create your first governed task
Turn a durable objective into an inspectable work order.
task api - Integrations
Cursor: integration design guide
Bring a development task into focus with Cursor. Choose the repository, define the intended change and review how editor tools use your project context.
- Articles
Data enrichment: adding attributes you can trace back to a source
What data enrichment is, the common types and sources, why matching and provenance decide its quality, and how to keep enriched records correct over time.
research - Journal
Decide what normal looks like before the first alert
Why a monitor needs a reviewed baseline and a written rule for material change before it runs, and why every version of that rule should be kept.
monitor - Articles
Deep research by AI agents: how it works and how to review it
How agent-led deep research plans, gathers sources, synthesizes and cites; when it is worth using, how to brief it, and how to review the report it returns.
research - Documentation
Define an enterprise-agent handoff
Share reviewed context across agent systems without merging their identities.
integrations