Hi everyone,

We have just merged the Human-in-the-Loop (HITL) feedback system. This
allows users to communicate back with agents and refine outputs through
multiple iterations.

Example DAG here:
[1]
https://github.com/apache/airflow/blob/main/providers/common/ai/src/airflow/providers/common/ai/example_dags/example_agent.py#L190

Best regards,
Pavan

On Tue, Mar 10, 2026 at 8:19 PM Kaxil Naik <[email protected]> wrote:

> Yeah, when we release that provider officially, Pavan & I might write a
> blog post on the Airflow site announcing it and the roadmap -- hoping to
> get some early adopter quotes / feedback too.
>
> On Tue, 10 Mar 2026 at 19:53, Pavankumar Gopidesu <[email protected]
> >
> wrote:
>
> > As of now not yet published any article. but we have curated a set of
> > examples here [1]. Article will be a good one :)
> >
> > [1]:
> >
> >
> https://github.com/apache/airflow/tree/main/providers/common/ai/src/airflow/providers/common/ai/example_dags
> >
> > On Tue, Mar 10, 2026 at 7:42 PM Jens Scheffler <[email protected]>
> > wrote:
> >
> > > Very cool!
> > >
> > > you presented some examples during monthly townhall, can we assume
> these
> > > examples are contained in source tree? Will there be a Medium article
> or
> > > so published with examples?
> > >
> > > On 10.03.26 09:25, Amogh Desai wrote:
> > > > This is really cool, thanks for sharing Kaxil and Pavan.
> > > >
> > > > Thanks & Regards,
> > > > Amogh Desai
> > > >
> > > >
> > > > On Thu, Mar 5, 2026 at 6:34 PM Kaxil Naik <[email protected]>
> wrote:
> > > >
> > > >> Hi everyone,
> > > >>
> > > >> Pavan and I have been working on AIP-99 native agentic AI for
> Airflow
> > 3.
> > > >> The first set of PRs have landed.
> > > >>
> > > >> The core idea: Airflow already has 350+ provider hooks, each
> > > >> pre-authenticated through connections. AIP-99 turns those hooks
> > directly
> > > >> into AI agent tools.
> > > >>
> > > >> What's available now:
> > > >>
> > > >> 1. HookToolset: wraps any Airflow hook into AI-callable tools with
> > > >>     explicit allowed_methods:
> > > >>
> > > >>     from airflow.providers.common.ai.toolsets import HookToolset
> > > >>
> > > >>     HookToolset(hook=S3Hook(aws_conn_id="my_aws"),
> > > >> allowed_methods=["list_keys"])
> > > >>
> > > >> 2. SQLToolset: 4 curated database tools (list tables, describe
> schema,
> > > >>     execute query, fetch results) scoped to specific tables.
> > > >>
> > > >> 3. DataFusionToolset — lets AI agents query files on object stores
> > (S3,
> > > >>     local filesystem, Iceberg) through Apache DataFusion. Agents get
> > SQL
> > > >>     access to Parquet, CSV, and Avro files without loading them
> into a
> > > >>     database.
> > > >>
> > > >> 4. MCPToolset: connects to external MCP servers via Airflow
> > connections.
> > > >>
> > > >> 5. Task decorators (Operators are also available :) ):
> > > >>     - @task.llm : single LLM call with structured output
> > > >>     - @task.agent : multi-step agent with tool access
> > > >>     - @task.llm_sql : text-to-SQL pipelines
> > > >>     - @task.llm_schema_compare : cross-database schema diffing
> > > >>
> > > >> LLM connections are configured through
> > > >> Airflow's standard connection model, supporting OpenAI, Anthropic,
> > > Google,
> > > >> Ollama, etc.
> > > >>
> > > >> HITL (Human-in-the-Loop) integration is also in progress as a draft
> > PR.
> > > >>
> > > >> Project Board:
> > > >> - https://github.com/orgs/apache/projects/586
> > > >>
> > > >> Summit talk where we previewed this:
> > > >> https://www.youtube.com/watch?v=XSAzSDVUi2o
> > > >>
> > > >> Separate from the AI work, AIP-99 also adds an AnalyticsOperator
> > powered
> > > >> by Apache DataFusion for high-performance SQL on object stores:
> > > >>
> > > >> - AnalyticsOperator — run SQL queries directly against S3, GCS,
> local
> > > >>    files, and Iceberg tables. Supports Parquet, CSV, Avro.
> > > >> - @task.analytics decorator — TaskFlow API support for the above.
> > > >> - Iceberg support via PyIceberg with Glue catalog integration.
> > > >>
> > > >> Pavan and I would love it if folks can start testing out and create
> > > GitHub
> > > >> issues if you run into bugs. Our intention is to keep it at 0.x
> > version
> > > so
> > > >> we can iterate on it faster. Looking forward to feedback.
> > > >>
> > > >> Thanks,
> > > >> Kaxil
> > > >>
> > >
> > > ---------------------------------------------------------------------
> > > To unsubscribe, e-mail: [email protected]
> > > For additional commands, e-mail: [email protected]
> > >
> > >
> >
>

Reply via email to