Sourcing and Outreach Agent

Your team spends more time finding people to contact than contacting them.

The agent works through the list they collect, decides which items genuinely fit what you offer, and drafts each message from your own case studies and references. Sales point it at leads, recruiters at candidates, bid teams at tenders, and it works the same way on any list your team answers by hand.


Running inside IWConnect. Up to 100 items read and scored a day.



Book a 45-minute call


What it does

It decides which ones are worth it, and why.

1

Your filters bring in the list

Sources, regions, keywords, roles. That part you already control, and the items arriving are already broadly relevant.

2

The agent qualifies each one

It reads the item and works out whether it genuinely fits what you offer, scoring that judgement against your services, your technologies, your certifications and your rules. Broadly relevant and actually worth approaching are not the same thing, and this is where the difference gets decided.

3

The reason is recorded, then reused

Every item that passes carries the reasons it passed. The agent writes the message from those same reasons, using your real material: the reference that matches, the work you have delivered, the write-up that proves it.

Your team opens a shortlist with drafts attached, instead of working down the full list one item at a time.

Where it looks

Wherever your list comes from.

Tender and procurement portals

Public calls, filtered down to the ones you can actually bid for.

Job boards and candidate pools

For recruiters, the same logic pointed at people instead of companies.

Hiring announcements and job posts

A company hiring three integration engineers is about to spend on integration.

Company news and funding announcements

A round raised is a budget about to be spent.

Your own CRM and existing lists

Records you already hold, scored again against what you offer today.

Set the filters once. Whatever they bring in, the agent works through it item by item.

Who it works for

If your work has this shape, the agent fits it.

A list arrives. Someone opens each item, checks it against what you offer, and writes a response to the ones worth answering. That is the whole pattern, and the department doing it makes no difference to the agent.



Sales and lead generation

Find the companies with the need you serve, and open with the reference that proves you have solved it.


Recruitment

Same agent, different target. Read the postings or the candidate pool, score against the role you are filling, and write the approach.


Bids and tenders

Read the calls as they are published, drop the ones outside what you deliver, and draft around your real references.


Partner and supplier screening

Work through inbound applicants or a market list, keep the ones that meet your criteria, and reply to those.


Grant and funding calls

Read the published programmes, keep what your work qualifies for, and draft the first response.


These are examples, not the list of what is supported. If your team does this with something not named here, nothing about the agent changes. Only the sources it reads and the rules it scores against.

How it works

Four steps, one loop.

1

Read

The agent pulls the values that matter out of each item: the industry, the technologies, the requirements. One item can carry several at once.

2

Score

A panel of models grades that reading against the same standard. One number per value, not an opinion.

3

Act or stop

Above the threshold, the agent writes the message. Below it, the item stops and waits for a person.

4

Improve

Every reading that scores perfectly is kept. Those become the training set for a specialised model that takes over the same task later, with no charge per item.

Why the messages are worth sending

It only writes when it understood the source.

Most outreach tools fail the same way. They fill a template, they get the context slightly wrong, and the person reading it can tell within one line.

This agent scores its own reading before it writes anything. An item it half understood never becomes a message. What does get written is built from your real material, so the proof attached to it is the proof that fits.

  • The message is not tied to one channel. It is written for the person and the reason they qualified, then delivered wherever your team works.
  • Volume is capped per person and the same contact is never approached twice.
  • Nothing sends itself. A person reviews and sends.
A reading and its score shown next to the message that was written from it
One source, ours

We pointed it at hiring posts, because that is the list our sales team was reading.

Every team has one source they check first. Ours is hiring announcements, because a company staffing up on a technology is about to spend on it. Yours might be a tender portal or a candidate pool. The agent does not care which.

It reads and filters The agent pulls the industries and technologies out of each post and scores its own reading. Industries and technologies are scored separately, so a post it half understood is caught rather than passed on whole. Every record links back to the original.
What survives is qualified, with reasons Those posts matched our services on industry, on technology and on meaning, with a score behind each match. Nobody had to work down the list deciding one by one.
Then it writes The agent drafts the message around the same references that made the match, and links the case studies that fit. Posts below the line never reach this step.

The draft lands where the team works. A person reads it and sends it.

Up to 100 posts a day, every day

A job post with its extracted tags beside the drafted message and the case studies it linked
Where we are

What is running, and what is not.

The agent runs inside IWConnect on our own lead generation.

100 items read and scored per day
2,000 verified examples added per month
2+ models scoring every reading
1 retraining cycle every week

The specialised model that would replace the general one is still training. It has not yet won, so that handover has not happened. We will show you the live comparison on the call.

The sourcing, the scoring and the drafting are live now.

Security and governance

Built to survive an audit.

Every item is logged with the source, the model version, the score and what happened next. Prompts and scores are traced. Every model version records the data and settings behind it.

  • Model access runs through a gateway, so the provider is a configuration choice.
  • Open models already run on infrastructure we control.
  • Nothing is sent without a person approving it.
An audit log showing each item with its source, model version, score and outcome
Pilot

Start with one source.

Pick the source your team scrolls most often. We point the agent at it, tune the scoring against what you offer, and within weeks you have a qualified list with drafts attached instead of a feed.

If the volume never justifies going further, you keep the sourcing and the scoring. That costs you one source rather than a programme.


Book a 45-minute call

Pilot timeline showing one source connected, scoring tuned, and drafts arriving
Questions

The ones we get asked first.

Is this a lead generation tool?

Lead generation is one use of it. The agent reads a list, qualifies each item against what you offer, and writes the response. Any work with that shape fits, whichever team does it.

How is this different from a template blast?

The agent scores whether it understood the source before it writes. Anything it did not understand well enough never becomes a message.

Which channels does it write for?

The message is written for the person and the reason they qualified, not for a channel. Where the draft is delivered is a matter of connecting it to the tool your team already uses. Our own deployment drops drafts into the CRM.

Can it use our sources, not just public ones?

Yes. Your own CRM records and lists work the same way as a public site.

Does this tie us to one AI provider?

No. Access runs through a gateway, so the provider is configuration.

Who runs it after launch?

Your platform team. Standard Kubernetes, standard monitoring, standard delivery.

Next Step

Tell us which list your team scrolls every morning.

We will tell you whether the agent can read it, how it would score against what you offer, and what your team would get back.

Talk to our team

A qualified shortlist with a drafted message attached to each item

    By ticking this box, you agree to ⋮IWConnect’s Terms & Privacy Policy. You also agree to receive future communications from ⋮IWConnect. You can unsubscribe anytime.