Jorge Gasca
Ver en español
Menu
Selected work

Live product demoPrivate source

Tonalli AI — One workspace for models, tools, and follow-up

Tonalli AI brings chat, tools, files, voice, messaging, generated artifacts, and scheduled prompts into one experimental workspace.

Open live productPrivate source
Tonalli AI guest workspace with model controls, a composer, tools, and artifacts.
Public guest flow2026-08-09The guest capture uses synthetic content and does not show an account, private prompt, or provider configuration.

30-second brief

RoleIndependent product builder
StageLive product demo
What I owned

I designed the interaction model, connected model and tool workflows, built persistence and messaging behavior, and tested scheduled delivery and its failure states.

Current result

The live demo now shows how a conversation can continue into a tool result or artifact, remain available in the workspace, and become a scheduled follow-up on the web or Telegram.

What I noticed

AI-assisted work becomes hard to continue when the conversation, source files, generated result, and reminder to act on it all live in different products.

What I worked on

  1. 01

    I designed the model, mode, streaming-chat, and agent-tool experience around one conversation.

  2. 02

    I connected saved chats, custom agents, memory, files, voice, messaging, and rendered artifacts.

  3. 03

    I made scheduled delivery record its outcome and added a plain-text Telegram retry when formatted delivery fails.

One decision that mattered

I persisted the delivery result, not just the schedule request. A reminder feature is only useful when the person can see whether delivery succeeded, failed, or needs another attempt.

What I learned

Tonalli AI pushed me to think beyond the chat response. The useful unit of work includes the artifact, the next action, and a visible record of what happened afterward.

Current status

Tonalli AI is a live product demo with private source. A guest workspace is publicly viewable, while provider-dependent actions require configured services.

See it in action

Tonalli AI

Public, synthetic, or simulated screens only. Customer and account data stay out of the portfolio.

01

I designed the model, mode, streaming-chat, and agent-tool experience around one conversation.

02

I connected saved chats, custom agents, memory, files, voice, messaging, and rendered artifacts.

03

I made scheduled delivery record its outcome and added a plain-text Telegram retry when formatted delivery fails.

Tonalli AI guest workspace with model and mode controls, a conversation composer, tools, and artifacts navigation.
Public guest flowTonalli AI on desktop.The guest capture uses synthetic content and does not show an account, private prompt, or provider configuration.
Tonalli AI guest workspace with model and mode controls, a conversation composer, tools, and artifacts navigation.
Public guest flowTonalli AI on mobile.The guest capture uses synthetic content and does not show an account, private prompt, or provider configuration.

A short synthetic flow from a conversation to an artifact and a scheduled follow-up.

Read the visual transcript

The walkthrough opens a synthetic conversation in the Tonalli AI guest workspace, shows the related artifact area, and finishes on the scheduling controls and delivery-status view. No private prompt is submitted and no provider delivery is claimed by the recording.

Public guest flowShort walkthrough of Tonalli AI.The guest capture uses synthetic content and does not show an account, private prompt, or provider configuration.

Technology

Next case studyZentix — AI agents that keep customer context together