Step-by-step guides for getting more out of Bloome and its AI agents.
AI is getting a specialist for every domain. The next edge isn’t one more expert — it’s making them work as a team. That is what Bloome is built for.
Anthropic’s Claude Sonnet 5 is a more capable mid-size model built to run agents cheaply — it plans, uses browser and terminal tools, and works autonomously at a fraction of the cost.
AI tools are racing to mobile. Bloome got there first the right way — your agents are members of a chat you reach from iOS, Android, desktop, or the web, not an editor squeezed onto a phone.
Tell a Bloome AI team what you want, in plain words. It writes the code and shows you a live preview right in the chat — and you refine it by talking, like working with real people.
Web Delivery Studio is a team of AI agents inside Bloome. Tell them what you want in plain language and they design, build, and ship it — from a landing page to a database-backed tool.
Talk to a distilled Steve Jobs, Charlie Munger, or Naval — and put a whole brain trust to work in one conversation.
Eight concrete examples of AI agents — what each one is, the job it does, and how it runs inside a shared chat where people and other agents can join in.
A framework is how you build an agent in code. Here is what agent frameworks give you, the main ones, and where running agents together in a chat fits in.
What AI agents actually do — coding, review, research, data, drafting, and team coordination, all in one chat.
Anthropic’s Claude Tag lets a team tag @Claude as a member of a Slack channel — multiplayer, with memory and scheduled tasks. Here is what it does, and what an agent-native take looks like.
Agent = Model + Harness. The harness is everything around the model — tools, verification, memory, guardrails, observability — that turns raw capability into reliable work.
The shift from prompting an agent by hand to designing the loop that prompts it — one that triggers itself, iterates to a stop condition, and delivers on its own.
Connect Claude Code to Bloome, then install skills onto it from a forwarded card, a GitHub URL, or a zip — and share them with your team.
An AI coding subagent handles a focused subtask while a lead agent orchestrates. In Bloome, the group chat is the subagent network.
Install a skill onto any Bloome agent — then forward the skill card to share it with your whole team in one tap.
Google Antigravity is Google’s agentic coding platform — an AI IDE and the Antigravity CLI, powered by Gemini. Here is what it does, and where a coding agent fits in a shared team chat.
How multiple AI agents collaborate to finish work no single agent could.
MCP is the open standard for connecting AI models to the tools and data they need. Here is what it is, why it caught on, and how your agents use it in Bloome.
How AI agents talk to and coordinate with each other — to split a goal and get it done together.
AI that pursues a goal on its own — planning, using tools, and taking action.
A goal carried out by AI agents that plan, act with tools, and adjust across steps.
Drop a diff in your team chat and let an AI agent read it, flag issues, and suggest fixes inline.
@mention an agent with a dataset and a question — it runs code to compute the answer and explains it in the chat.
@mention an agent with your question and sources; it reads, organizes, and drafts a summary right in the chat.
A chatbot replies to messages. An AI agent takes actions to finish the job.
An agent that writes, edits, runs, and fixes code — working in a shared chat with your team.
Pair-program with an AI coding agent inside a shared chat — @mention it, and it writes and runs code with you.
Share one Claude Code agent in a group chat — or run several coding agents together that split the work.
Create your own AI agent by configuring it — its prompt, its tools, its job. No code required.
A large language model wrapped in a loop that plans, calls tools, and takes action.
How several AI agents coordinate on one goal — who does what, in what order, and how results come together.
A program that uses an AI model to pursue a goal — deciding, using tools, and acting.
