@ChatBotKit

ChatBotKit helps you create conversational AI chatbots with your own data to communicate naturally with users on your website, Slack, Discord and WhatsApp.

chatbotkit.com
Joined December 2022
  • Tweets572
  • Following45
  • Followers259
192Media
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
Your API key called. It would rather stay out of the screenshot. Tokens and secrets now stay masked until you reveal them. chatbotkit.com
ChatBotKit card headed "Keep credentials hidden on screen." An illustrative panel shows two locked fields, "Token" and "Private key", filled only with mask dots; the private key spans four lines. Text below: "Tokens and secrets are masked in the Blueprint Designer and on settings pages until you reveal them. Multi-line keys too, like private keys." Footer: Illustrative, chatbotkit.com.

ALT ChatBotKit card headed "Keep credentials hidden on screen." An illustrative panel shows two locked fields, "Token" and "Private key", filled only with mask dots; the private key spans four lines. Text below: "Tokens and secrets are masked in the Blueprint Designer and on settings pages until you reveal them. Multi-line keys too, like private keys." Footer: Illustrative, chatbotkit.com.

5
Replying to @imsachinshah0
Give the human handoff a packing list: extracted field, source page, rule version and reason for review. “Low confidence” alone is homework.
5
Replying to @Born_TechK
Give prices their own seatbelt: assert the exact amount, currency and billing period against the source. “On topic” won’t pay for a missing zero.
1
1
7
Replying to @trycua
My vote for the next run: 30 minutes of browser work, with p95 step latency. Give the sprinter a marathon bib.
27
Replying to @cursor_ai
A useful design note: element + viewport + expected behaviour. “This button wraps at 360px” beats “make it pop” every time.
8
Replying to @trq212
Ship each customisation with a test for the behaviour you meant to keep. A clean merge can still delete your favourite trick.
3
Replying to @AvinashDalvi_ @ataiiam
Keep the fork thin: OpenDuet puts branding, bots and skills in one tenant folder. Patch ownership still needs a human name on it.
10
Replying to @LangChain
Move the parrot. Keep the rest of the jungle. Editable beats regenerate-and-pray.
44
Your app. Your UI. No need to reinvent the chat wheel. Swift + React Native SDKs: docs.cbk.ai/swift-sdk docs.cbk.ai/react-native-sdk
ChatBotKit SDKs. Bring AI chat into your app. Two abstract chat panels compare Swift, streaming chat for Apple apps, with React Native, headless hooks for your native UI. The React Native panel uses dashed outlines. A coloured edge marks each active response. Footer: Start with the SDK docs, cbk.ai.

ALT ChatBotKit SDKs. Bring AI chat into your app. Two abstract chat panels compare Swift, streaming chat for Apple apps, with React Native, headless hooks for your native UI. The React Native panel uses dashed outlines. A coloured edge marks each active response. Footer: Start with the SDK docs, cbk.ai.

1
1
63
Understand the setting. Keep building. In ChatBotKit’s Blueprint Designer, hover over or focus a field label for help. Click the label to show the explanation below the field. Field help is now live. chatbotkit.com

ChatBotKit | AI Agents for Support, Sales, and Operations

Build AI agents from ready-made solutions and let them work in the background - on schedules and triggers, connected to your tools, in every channel. ChatBotKit keeps them running, with security and...

chatbotkit.com
1
1
53
Replying to @liquid_richie @liquidai
Thanks, that separates generic tool calling from adaptation to a specific setup. For deployment, we would still check held-out schemas and multi-step recovery in the target harness. Is there a recommended fine-tuning example for that path?
1
1
23
Replying to @liquidai
Do the tool-use gains transfer between harnesses without retraining, or depend on matching the training harness and tool schemas? A cross-harness breakdown would help builders decide what to evaluate before deploying locally.
1
1
72
Replying to @poteto
When a mistake recurs, do you turn it into a regression test, a type constraint or a written agent instruction? The first two make the lesson executable; curious how you choose which layer should own it.
12
Replying to @LangChain
A reaction is a useful receipt. Do you distinguish queued, running and finished? People need to know whether to wait or intervene.
7
Replying to @cursor_ai
Do your evals cover interrupted runs and repeated tool calls, or mainly the final answer? Those are often where a promising demo turns into an unreliable workflow.
4
Ask your bot to work in the background. Get an update where you started. Turn notifications on for a task your bot creates in a supported conversation. It replies with a text update when the run ends. Illustrative Slack example. docs.cbk.ai/task-notificatio…
1
1
52
Start with the work. Choose the computer it needs. Shell for commands, tools and files. Desktop for a Linux desktop you can see and control in your browser. What will your agent build with ChatBotKit Computer? chatbotkit.com
ChatBotKit Computer card asks What does the work need? Subheading: Two ways to give your agent a computer. Two panels compare Shell, Commands, tools and files, with Desktop, See and control it in your browser. Shell has a terminal symbol; Desktop has a monitor and pointer. ChatBotKit logo and chatbotkit.com appear above.

ALT ChatBotKit Computer card asks What does the work need? Subheading: Two ways to give your agent a computer. Two panels compare Shell, Commands, tools and files, with Desktop, See and control it in your browser. Shell has a terminal symbol; Desktop has a monitor and pointer. ChatBotKit logo and chatbotkit.com appear above.

1
2
336
Start with a task. Choose Shell or Desktop. Connect your agent and give it the work. Four cards to imagine your first workflow with ChatBotKit Computer. Task and outputs shown are illustrative. What will you build? chatbotkit.com
ChatBotKit Computer, card 1 of 4. What will your agent build? Start with the work you want to do. Illustrative task: turn this CSV into a report. Other ideas: check a signup flow, build a landing page, tidy data.

ALT ChatBotKit Computer, card 1 of 4. What will your agent build? Start with the work you want to do. Illustrative task: turn this CSV into a report. Other ideas: check a signup flow, build a landing page, tidy data.

Card 2 of 4. Choose the computer the work needs. Shell: commands, tools and files. Desktop: a Linux desktop you can see and control in your browser.

ALT Card 2 of 4. Choose the computer the work needs. Shell: commands, tools and files. Desktop: a Linux desktop you can see and control in your browser.

Card 3 of 4. Connect your agent. Give it the task. Illustrative Agent connects to a running Linux Computer with commands, tools and files, producing report.md, data.csv and site/.

ALT Card 3 of 4. Connect your agent. Give it the task. Illustrative Agent connects to a running Linux Computer with commands, tools and files, producing report.md, data.csv and site/.

Card 4 of 4. See where the work goes. The files your agent makes live on its computer. Illustrative files: report.md, data.csv and site/. ChatBotKit Computer, chatbotkit.com.

ALT Card 4 of 4. See where the work goes. The files your agent makes live on its computer. Illustrative files: report.md, data.csv and site/. ChatBotKit Computer, chatbotkit.com.

1
1
63
Give the work somewhere to happen. A CSV becomes a report in this illustrative workflow: commands, tools and files, connected through ChatBotKit Computer. What will your agent build? chatbotkit.com
1
2
78
Keep the conversation moving. Bring the screen into view. ChatBotKit Computer lets your agent share desktop snapshots in Slack, Telegram or Discord. Open the desktop in your browser to see and control it. What would you build together? chatbotkit.com
1
2
109
Load more