Level 01
Supervised
You review every action before it happens.
- Reads
- Asks
- Edits
- Asks
- Commands
- Asks
An AI assistant for your developers
Meet Nx IDE.
Describe a task in plain English. Nx IDE reads your project, plans the work with you, writes the code and tests it, inside VS Code, the code editor many developers already use. It works with the AI model you choose, even one on your own computers, and by default it changes nothing without your approval.
31 ready-made specialists 26 AI providers, or your own Sends nothing to Nexgile
Nx IDE installs into VS Code as an add-on called Nexgile Code. A Nexgile license key switches it on.
One platform
Nx·Studio designs your digital workers. Nx IDE gives your developers an AI assistant. The Cognitive Engine takes over routine decisions once it has proved itself.
See how the platform fits together What it is
An AI assistant in your code editor.
You describe a task in everyday words. Nx IDE reads your project, plans the work, writes the code and runs the tests. By default, it asks before it changes anything.
The problem it solves
Faster work that still gets checked.
Many AI coding tools leave all the checking to you. In Nx IDE's team mode, called Orchestrator, one specialist writes the change and two others test and review it. They are built to stop and ask before any work goes out.
Who it's for
Teams that must check every change.
Software teams in regulated or security-minded organizations, and teams modernizing older systems. They get AI help with approvals built in, controls an auditor can check, and no tie to a single AI company.
How a task works
One task, from request to checked result.
Five steps, and you decide how much of it runs without asking you first.
01
01
Say what you need
Type the task in plain English. Pick a specialist if you like, such as Plan for planning or Debug for fixing problems. Then point it at the files to use, including PDFs and Word or Excel files.
02
02
Agree the plan
For bigger jobs, the Plan specialist writes a plan first. Comment on any part and only that part is rewritten. Nothing is built until the plan is approved, by you or, on a more hands-off setting, after a countdown.
03
03
Approve it, or let it run
By default, every change and command waits for your OK. A five-level setting called the Delegation Dial, plus rules you write, can let some actions run on their own. Before code is saved, shared or released (committed, pushed or deployed), the AI is built to stop and ask. A deny rule blocks an action at every level.
04
04
Every step can be undone
As it works, it saves your files at each step (checkpoints), so you can go back to any earlier point in one click. A live meter shows the estimated cost as it goes.
05
05
It checks the result
By default, after changing files it reviews its own work, builds the project and runs your tests. Then it tells you exactly what it changed.
the AI you choose
Pick the AI. Switch any time.
Choose from 26 AI providers, from the major AI companies to services that host open models, or run a model on your own computer. Switch whenever you like; you are never tied to one supplier.
Keep it in-house
Run AI models on your own machines with tools such as Ollama or LM Studio, so your code stays on your own hardware.
Use what you already pay for
Use an AI subscription you already pay for, or the AI models built into VS Code.
The right AI for each job
Each specialist can use its own AI model, so planning, coding and reviewing each get the best fit.
Keys stay locked away
The access keys for your AI accounts stay in your computer's secure storage, not in settings files.
private by design
Your code never passes through us.
Your code travels straight from your editor to the AI provider you picked. Nothing from Nexgile sits in between, Nx IDE sends us no usage data, and even the license check works offline.
No usage reports
Nx IDE sends no usage reports (often called telemetry). We never receive your code, what you type or how you use the tool.
No middleman
Requests go straight to your chosen AI provider, or never leave your computer if the model runs there.
An edition for US government buyers
A separate TAA edition, built for the US Trade Agreements Act, leaves out restricted AI providers and models entirely. They cannot be switched back on.
Hide private files
List files or folders in a special “ignore” file (.nexgileignore) and the AI will not read them.
understands your code
It maps your code before it changes it.
A feature called Cortex builds a private map of your code, on your own computer. It shows how the parts connect and what a change could break, before anyone makes it. It even reads older languages such as COBOL.
A map of your code
See what a change would touch before you make it. The map is built on your own computer, with no internet needed.
Older code, too
It reads COBOL alongside modern languages, so older systems sit on the same map.
Remembers your project
It keeps notes on your project between sessions and can look up decisions from earlier chats.
Reads what you read
It can read PDFs, Word and Excel files, and web pages. If you switch it on, it can also look into other code projects.
safety nets
Guardrails the software enforces.
Beyond approvals, Nx IDE refuses unsafe file changes and can limit where the AI may write. With the optional sandbox, your own operating system stops its commands from changing anything outside your project.
Save points
On by default. The AI saves a checkpoint of your files as it works, so you can roll back in one click.
Clear boundaries
Draw a line around the folders the AI may change. Automatic tasks stay inside the folders you pick, and the software makes sure of it.
A sealed-off sandbox
Optional on macOS and Linux. Commands may change files only in your project and the folders you allow, and can be cut off from the network.
No half-written files
It will not save a half-finished file. Changes that were cut off, or that skip code with a note like “rest of the file unchanged”, are refused.
specialists & skills
The right specialist for each job.
31 built-in specialists, from Plan and Code to Tester, Reviewer and Shipper, each focused on one part of the job. Add your own, or install extra skills and tool connections from the built-in marketplaces.
31 built-in specialists
Ten core roles plus 21 ready-made experts for everyday jobs, from tidying up code to changing database structures.
Make your own specialists
A short text file is all it takes to add a specialist. Your team reviews it and keeps its history, like any other change.
Skills & tools in one click
Install skills (reusable instructions) and tool connections from the built-in marketplaces, or write your own once and reuse them.
Follows your project's rules
Instruction files in your project, such as AGENTS.md, tell every specialist how your team works.
team mode
An AI team, with you as the lead.
In Orchestrator mode, one specialist (or a small team) writes the change, two others check it independently, and a person decides whether it goes out.
01 Code · or a team
Implement
One specialist, or a team of 2 to 5
02 Tester · Reviewer
Test + Review
Side by side, each on its own
03 You
Ship?
An approval question to you
04 Shipper
Ship
Saves it to a separate copy (a branch)
Independent checks
The tester and reviewer start fresh, with only the request and the changed files, so the writer's reasoning cannot sway them. Neither can edit files.
Limited retries
If tests fail or changes are needed, a fresh specialist tries again, at most twice. Then the decision comes back to you.
One button stops them all
Hit Stop and all AI helpers stop together. You can also see a map of who is working on what.
Many AI helpers
Agent Manager
One screen to run several AI chats at once and follow each helper's progress, cost and questions.
Many AI helpers
Agent Teams
For larger jobs, 2 to 5 AI helpers (agents) split the work, for example the server side and the screens people see. They message each other and share a task list while you watch.
Many AI helpers
/batch
Break a large change into as many as 30 small tasks. Several run at once, each in its own copy of the code. If you choose, each becomes a draft pull request (a proposed change) on GitHub.
Many AI helpers
/review
Ask up to five AI helpers to review your changes side by side. They edit nothing, and nothing gets fixed until you choose.
The Shipper is instructed to save work to a separate branch and never overwrite anyone else's. “Ship?” is a question to you: at the Supervised and Trust Reads levels it always waits for your answer. At higher levels, add a deny rule if shipping must always wait for a person.
Built-in controls
Change control, built into the AI.
The same approvals your team uses for any code change, built into the AI helpers themselves.
01
Approval
Approval by a person is on by default.
02
Written rules
Write rules that allow an action, ask first or block it. Anything a rule allows names the rule that allowed it.
03
Asks before shipping
Before code is saved, shared or released, a database is changed or anything is deleted, the AI is built to stop and ask. A deny rule makes it a hard stop at every level.
04
Your own checks
Your own scripts (hooks) can run at set moments, for example to make your quality checks pass before a task counts as done.
05
Protected settings
Your permission, hook and plugin files are off-limits to every AI helper. The main helper must ask before it changes its own rule files.
06
Separate roles
The AI helpers that test and review code cannot edit files.
Tool access, rules, hooks and the sandbox are enforced by the software itself. They are not just instructions the AI is asked to follow.
The security test
What your security team will ask first.
Who approved that change? What did it cost? Who was allowed to touch the code? Nx IDE gives a clear answer to each.
Q1
Who approved that change?
Every change traces back to a person: they approved it, or they chose the setting or rule it ran under. Out of the box, it pauses for a yes before saving, sharing or releasing code.
Q2
What did it cost?
While a task runs, you see its estimated cost. The Usage & Cost dashboard sorts spending by project, AI model and day, and warns you before you pass your budget. If you set a limit, it stops there and waits for you.
Q3
Who was allowed to touch the code?
Only what your settings and rules allowed. Deny rules apply to every AI helper, including helpers started by another helper. None of them can edit your permission or hook files, and the tester and reviewer cannot edit any files.
Most safeguards are settings or rule files. Your security team can read them, store them with your code, and match each one to the controls they already use.
Visit the Trust Center the delegation dial
Hand over more, one step at a time.
One dial under the chat box sets how much the AI may do without asking. Start fully supervised and turn it up as your trust grows.
Good to know: save points (checkpoints) are on by default at every level. Above Supervised, helpers started by another helper (such as the Orchestrator's specialists) run with every automatic approval switched on. Your deny rules still apply to them.
More review More autonomy
Level 02
Trust Reads
Reading files inside your project runs on its own. Edits and commands still ask.
- Reads
- On its own
- Edits
- Asks
- Commands
- Asks
Level 03
Trust Edits
Reading and editing files run on their own. Routine questions, including plan approval, get the AI's first suggestion after a 60-second countdown. Commands still ask.
- Reads
- On its own
- Edits
- On its own
- Commands
- Asks
Level 04
Trust Execution
Reading, editing and commands run on their own, as do tools you have marked as always allowed. Starting more helpers, editing protected files or files outside the project, and a few other actions still ask. Deny rules still block.
- Reads
- On its own
- Edits
- On its own
- Commands
- On its own
Level 05
Autonomous
Everything runs without asking, with three exceptions. Your deny rules still block. Edits to protected files or files outside the project still ask, as do a few actions such as fetching web pages.
- Reads
- On its own
- Edits
- On its own
- Commands
- On its own
A whole team in one tool
The core team.
Ten core roles, each focused on one part of the job. The Orchestrator can bring several of them onto a single task.
Plan
Plans and designs before any code is written.
Code
Writes, changes and tidies up your code.
Chat
Answers questions and explains how things work.
Debug
Finds and fixes problems, step by step.
Orchestrator
Leads a team: writer, tester, reviewer, shipper.
Tester
Checks a change independently.
Reviewer
Gives an independent code review.
Shipper
Saves and uploads approved work.
Spec Bootstrap
Interviews you and writes a project guide (wiki).
Spec Sync
Keeps that guide up to date as the code changes.
Plus 21 ready-made specialists for everyday work
RefactorTest GenDoc GenSecurityAPI ModDep UpgradeIssue FixerPR FixerMerge ResolverDocs ExtractorIssue InvestigatorIssue WriterDB MigratorDB ArchitectCode ArchitectDevOpsAPI TesterCode ReviewerTranslateUI DesignerDev
Want one that isn't listed? Put its description in a small text file (Markdown format), and it shows up for one project or all of them.
Everything it can do
Help from first plan to final release.
Nine areas where it helps. In every one, you decide how much it does alone.
Plan & design
Agree the work before any code is written.
- A plan document you can comment on, part by part
- Sketch the overall design up front
- Build and maintain a project guide (wiki)
Build & update
Write, improve and modernize your code.
- Write, change and tidy up code
- Update older code, upgrade the libraries it uses, translate it
- Work with older code, including COBOL
Test & verify
Catch problems before your users do.
- Write tests for your changes
- A self-review and test run when a task ends
- An independent tester in every Orchestrator run
Review & release
An independent review, then a controlled release.
- /review — up to five reviewers at once
- Every edit shown for your approval, by default
- Asks before it ships, to a separate branch
Understands your code
Knows the whole project, not just one file.
- Cortex: a private map of how your code connects
- Memory between sessions, and search across past chats
- Search by meaning, after a one-time setup
Connects to your tools
Works with the systems your team already uses.
- Add connections to your other tools and systems
- One-click tools and skills from built-in marketplaces
- Optional: opens the app it built on your machine to check it works
Stays in control
Speed inside limits you set.
- Approval on by default; the Delegation Dial for the rest
- Written allow / ask / deny rules, and your own checks (hooks)
- An optional sandbox that walls commands in
- A Usage & Cost dashboard with budget alerts
Works at scale
From one chat to many AI helpers at once.
- Agent Manager: many chats side by side
- Agent Teams of 2 to 5 that coordinate
- /batch: up to 30 tasks, each in its own copy of the code
Works your way
Fits how your team already works.
- A save point at every step — restore in a click
- Optional typing suggestions and voice dictation
- Plain English → a ready-to-run command
- Chat in VS Code, or open it in a browser tab
Recently added
What's new in Nx IDE.
- Teamwork
Agent Teams, Agent Manager and /batch
Run many AI helpers at once and let small teams coordinate. Split big changes into tasks that run side by side, each with its own draft pull request if you choose.
- Planning
Plans you can review, and /review
Mark up the plan with comments before any code is written, then have up to five reviewers check the result together.
- Control
Written rules, hooks and a sandbox
Decide what is allowed, asked or blocked, add custom checks that run at key moments (hooks), and use an optional sealed-off space (sandbox) on macOS and Linux.
- Context
Memory, research and a cost dashboard
It remembers your project from one session to the next, and it can read websites and documents. The Usage & Cost dashboard tracks spending and sends budget alerts.
- Models
Recent AI models
New models from the major AI providers, ready to pick from the model list.
Good to know
What's on, what's optional.
Optional — off until you turn it on
- Operating-system sandbox (macOS and Linux)
- Per-task request and cost limits
- Web search and research in other code projects
- Opening the app it built in a browser to check it (needs Chrome or Edge)
- Automatic note-taking for project memory
- Typing suggestions, read-aloud and voice dictation (dictation needs the FFmpeg tool and a speech-to-text key)
Needs a one-time setup
- Searching your code by meaning
- Tool connections — add the ones your team uses, or install them from the marketplace
Will it act without my approval?
Only with your say-so.
Approval starts switched on. The Delegation Dial, together with your rules, controls how far it goes alone. At higher settings, helpers launched by other helpers also act without asking, though nothing on your deny list is ever allowed.
Can it run up a bill?
You see the estimated cost as it works.
Daily and monthly budget alerts warn you but do not stop the work. Optional per-task limits pause it until you decide.
Which AI models can we use?
Any of 26 AI providers, or 21 in the TAA edition.
If a model runs on your own computers, your code stays in the building.
Does our code go to Nexgile?
No.
We get no reports on how you use it (no telemetry), and no Nexgile service sits in between. Your code reaches only the AI provider you pick.