Skip to content

    Free Recommendation

    Tell us what you want fixed

    We will reply with a practical recommendation. Free scoping call included.

    We use these details only to answer you, and we delete enquiries that do not become work after 24 months. The page you sent this from goes with it, so we know which parts of the site are useful. See the Privacy Policy.

    Conversational Image Editing Agent

    Handles creative asset editing and library management for content and creative teams managing a shared asset library.

    What This Automation Does

    1. 1Takes an editing request as a chat message
    2. 2Routes the request to the right operation rather than a fixed branch
    3. 3Searches the Drive library for the raw files or prior generations it needs
    4. 4Applies the edit, or combines images, then files and renames the result
    5. 5Returns the finished image in the same conversation

    Why we built it

    We built this because the slow part of small image work is not the edit, it is finding the right source file and putting the result back where the team expects it. Giving the agent tools over the library rather than just an editing model is what removes that overhead.

    Problem It Solves

    Creative asset editing and library management

    Best For

    Teams making frequent small edits to a shared asset library
    Content teams working from a phone
    Businesses without design software on every desk
    Teams whose asset library has stopped being navigable

    Business Benefits

    • Remove the file-hunting around every small edit
    • Keep edited assets filed and named consistently
    • Make routine edits possible without design software
    • Keep the asset library usable as it grows

    What the AI does here

    • Tool-calling AI agent

      A model that decides which action to take and calls the connected tools itself, rather than following a fixed branch.

    • Tools the agent can call×5

      The specific capabilities exposed to the agent - search, HTTP calls, sub-workflows, or a system of record it can read and write.

    • Conversation memory

      Prior turns are carried into the next call, so the system holds context across an exchange instead of treating each message as the first.

    • Language model call×2

      A direct model call for classification, extraction, drafting or scoring at a defined point in the flow.

    As built, this one runs on Anthropic, OpenRouter. Model and provider are chosen per engagement against your own accounts, cost tolerance and data-residency requirements — nothing here is fixed to one vendor.

    Tools Connected

    ✈️Telegram

    The conversation the editing request arrives in and the result is returned to.

    📁Google Drive

    The asset library the agent searches, writes back to, and renames within.

    🧠Anthropic

    Runs the agent that decides which editing tool to call for a given request.

    🤖OpenAI

    Handles the lighter classification and routing calls alongside the main agent.

    Available as

    A build we deliver for you

    Adapted to your systems, your data and your process — not dropped in as-is. Scoped and quoted per engagement.

    Systems connected4
    AI components4

    Architecture

    Workflow Architecture

    How this automation moves data, applies logic, connects tools, and produces business outcomes.

    Chat Request

    trigger

    Request Routing

    router

    Editing Agent

    ai

    Drive Library Lookup

    database

    Result Filed & Returned

    notification

    Edited Image

    output
    Complexity
    Advanced
    AI
    Steps in the build

    14

    Operational steps counted in the workflow

    Systems connected

    4

    Telegram, Google Drive, Anthropic…

    Departments Impacted
    Marketing
    Operations

    Want this adapted to your process?

    Related builds

    HubSpot Apollo Lead Scoring

    Handles lead capture and management for sales teams and B2B companies.

    Reduce manual lead review and qualification time

    AI
    4 integrations
    🟠HubSpot
    🚀Apollo
    💬Slack
    +1

    Typeform AI Proposal Generator

    Generate branded PDF proposals automatically from Typeform submissions and link to HubSpot deals — for B2B sales teams, agencies, and service businesses using Typeform for lead capture.

    Reduce manual lead review and qualification time

    AI agent
    3 integrations
    🟠HubSpot
    📁Google Drive
    📋Typeform

    Typeform Lead Enrichment

    Handles lead capture and management for sales teams and B2B companies.

    Reduce manual lead review and qualification time

    AI
    4 integrations
    🟠HubSpot
    🤖OpenAI
    🐵Mailchimp
    +1

    AI Expense Receipt Capture

    Handles expense capture and reconciliation for finance teams and operations managers.

    Remove manual re-keying of receipt data

    AI agent
    4 integrations
    📊Google Sheets
    ✈️Telegram
    🔗OpenRouter
    +1