01 · in pieces
Work arrives in pieces.
A request buried in a group chat. The ticket in another project. The decision nobody wrote down.
The AI Workspace · by The Code Lawyers
Brilliant at the boring bits.
Lamp is the AI workspace for businesses that would rather be brilliant than busy. Put it in your team’s chats, plug it into your ERP or CRM, or have us build an app around it.
02 · lining up
Lamp lines them up.
It works out where each request belongs, finds the right ticket, reads before it changes anything and checks the result after.
03 · one line back
You get one line back.
“Done. CLM-42 is in progress.”
Seen from the lamp, the scattered pieces make its mark.
the platform
Not another chatbot. An entire workspace.
Most AI tools stop at the reply. Lamp keeps going: it remembers, routes, files, assigns and follows through, then tells you what it did in a line. And it goes where your business runs: chats, ERP, CRM or an app built for you. One assistant, a whole system behind it.
01 · workspaces live
A private corner for everyone.
Every person gets a profile, a page of notes, a journal and a folder for files. Lamp keeps them current as it works.
See it workintelligence
Smart enough to be brief.
Lamp answers in a sentence or two. No feature menus, no cheerleading, no “want me to check?”. It checks, then tells you. Same Lamp in every chat app, and inside your own software too.
try a message
Today
move the launch ticket to in progress
Done. CLM-42 is in progress.
Illustration. Names and tickets are made up; the steps are the ones Lamp runs.
- request
- “move the launch ticket to in progress”
- route
- Main (CLM)default project
- find
- CLM-42 · Launch checklist
- read
- status: To Do
- change
- To Do → In Progress
- read back
- status: In Progress✓
- reply
- “Done. CLM-42 is in progress.”
automation
Busywork just met its off switch.
You ask once. Lamp takes the other steps: works out where the request belongs, finds the work, reads it, changes it, reads it back and tells you in a line.
- Creates tickets, after a duplicate check
- Edits summaries and descriptions
- Comments and moves status
- Assigns by name or email
- Routes work to the right project
- Writes files and delivers them
Works with Jira Cloud and Jira Server/Data Center today. Before creating anything it checks for duplicates; if a write times out, it checks whether the change landed before trying again. Account IDs stay inside the integration.
collaboration
The colleague in every thread.
Mention Lamp in a channel and the whole team gets the answer: what’s left, who owns it, where the file went. Ask it to hand work to someone and it’s done before the next message. What each person tells it in private stays theirs.
- Answers in the channel, for everyone in it.
- Assigns teammates by name or email.
- Finds the right person in your directory.
- Shares the work, never anyone’s private notes.
@Lamp what’s left before launch?
Two tickets: CLM-44 copy review (Ana) and CLM-47 QA sign-off, unassigned.
@Lamp give CLM-47 to Priya
Done. CLM-47 is assigned to Priya Shah.
✅ 3
on it
@Lamp post the launch notes here
Here you go.
launch-notes.mdMarkdown · 3 KB
Illustration. The team and tickets are made up.
Users/ana
Sandbox/ana
Stable facts and decisions Lamp saves while it works.
- Release moved to Friday after the QA review - Weekly report goes to the #ops channel - Default board for design work: DES - Don’t assign tickets to the contractors
workspaces
A private workspace for every person.
Everyone gets their own corner of Lamp: a profile, a page of notes, a journal and a folder for files. Lamp keeps them current as it works and looks back through them when you ask. It won’t claim to remember what isn’t written down.
- in
- Markdown, text, CSV, JSON and code
- 1 MB each
- out
- Files Lamp writes, sent as attachments
- to your chat
- space
- A private folder per person
- 8 MiB · 256 files
- notes
- Plain Markdown you could read yourself
- 256 KiB a file
- not yet
- PDF, Word and images
- planned
guardrails
Lit where you’re working. Dark everywhere else.
Lamp gets a short list of tools and nothing else. Every call is checked against that list three times: when tools are offered to the model, when a call is dispatched and when it runs. Anything outside it is refused before it starts.
try to make lamp misbehave · simulated in your browser
Pick one. The lamp will tell you.
Can use
Your folder and notes
- lamp_read
- lamp_write
- lamp_list
- lamp_memory_read
- lamp_memory_write
- lamp_recall
Jira
- jira_route
- jira_search
- jira_get
- jira_create
- jira_update
- jira_comment
- jira_transitions
- jira_transition
- jira_assign
- jira_members
- jira_find_user
Switched off
- Shell and terminal
- SSH
- Web browsing
- Running code
- Handing work to other agents
- Scheduled automations
- Changing its own settings
- Shared memory between people
Refused paths
- Absolute paths
- ../ traversal
- Hidden files
- Device names like CON or NUL
- Symlinks, junctions and hard links
These limits are enforced by the application, not by an operating-system jail. We’d rather tell you that than oversell it. Jira actions use the connected account’s permissions, so connect an account with the access you intend.
reliability
If one model fails, another answers.
Backup brain included. Lamp runs on a primary model with an automatic fallback to a second provider. It switches when the provider fails, not as a race on every message, so you get one reply either way.
Primary provider answering.
- Encrypted snapshots
- every 60 seconds, the last five kept
- One worker at a time
- so two copies never answer the same chat
- Encrypted backups
- you can download and restore
- Model names
- never shown in chat; the provider list is available on request
roadmap · october 2026
Live today. Lit up next.
We’re building an ecosystem, not a feature. Here’s exactly where it stands, without the fog.
Live today
- Private workspaces and memory for every person
- Ticket automation that reads every change back
- Team channels and direct messages
- Text files in, finished files out
- A second model on standby
- Encrypted snapshots and backups
- Lamp inside Colyf, on the web and mobile
- Integration into your ERP, CRM or internal tools, built with our team
- A custom web and mobile app with Lamp inside, built by The Code Lawyers
Lit up next
- Reading PDFs, Word documents and imagesText, Markdown, CSV, JSON and code files work today.
- An operating-system sandbox under today’s limitsToday’s limits are enforced by the application.
- Signing up on your ownAccess is by request for now.
Never
Pretending. Lamp recalls saved notes and past conversations, and says so when it can’t find something.
questions
Plain answers before you ask.
If something isn’t settled for your team, we’ll say so and put the answer in writing.
Ask us anythingWhat exactly is Lamp?
An AI workspace for businesses. Every person gets a private workspace with memory and files; the team gets an assistant that automates the busywork, answers in shared channels and delivers finished files. It lives in your chats, inside your own software, or in an app we build for you.
Can Lamp work inside our ERP, CRM or other software?
Yes. We integrate Lamp with the systems you already run, whether that’s an ERP, a CRM, HR, finance or your internal tools. It uses your app’s own permissions: it reads what each person is allowed to see, prepares the change, and acts once they confirm. That’s how it already works inside Colyf.
We don’t have the right software. Can you build it?
Yes. The Code Lawyers designs and builds web and mobile apps, and we can build yours with Lamp inside from day one, so your team gets the product and the assistant together.
Which chat apps does Lamp work in?
Telegram, WhatsApp and Slack. Inside Colyf, Lamp also works on the web and on mobile, with its own separate setup.
Who can see my notes?
Your profile, notes and journal belong to you, and other users can’t read them through Lamp. The people who run your Lamp deployment manage the server it runs on, so ask us how that’s set up for your team.
Does Lamp train on our conversations?
Lamp doesn’t train models. Requests are processed by model providers under their API terms. Ask us for the provider list and those terms.
Where is our data stored, and for how long?
Ask us. We’ll put the hosting location, retention and deletion process in writing for your team before you start.
Can Lamp change things without asking?
It acts on clear requests and tells you what it did. It reads a ticket before changing it and reads it back after. When something essential is missing, it asks one short question first.
What can Lamp do in our Jira?
What the connected account can do, limited to the actions Lamp has: search, read, create, edit, comment, assign and move status. There is no delete. Connect an account with the access you intend.
Is this the same assistant that’s inside Colyf?
Same family, separate integrations. In Colyf, Lamp works inside the platform on the web and mobile and proposes changes you confirm. The assistant in your chat apps has its own identity, memory and tools.
How do we get access?
Email us with your team size and where you want Lamp: your chats, your software, or a new app. We’ll reply with the next steps.
Make light work of it.
In your chats, inside your ERP or CRM, or in an app we build for you. Lamp is available by request.