@sellable/install 0.1.129 → 0.1.130
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/bin/sellable-install.mjs
CHANGED
|
@@ -685,7 +685,7 @@ clear business decisions, tradeoffs, and approval gates. Use product language:
|
|
|
685
685
|
- "I can create a draft shell for you to watch with approval gates before
|
|
686
686
|
sourcing", not mutation jargon
|
|
687
687
|
|
|
688
|
-
When explaining
|
|
688
|
+
When explaining source decisions, show the concrete counts behind the
|
|
689
689
|
logic: lanes searched, timeframe, raw result counts, finalist posts or preview
|
|
690
690
|
rows, sampled people, sampled fits as n/N (%), estimated usable people, and the
|
|
691
691
|
confidence basis. Never show a percent like "73% match" without the numerator,
|
|
@@ -700,22 +700,27 @@ label it explicitly as not estimated from this run.
|
|
|
700
700
|
|
|
701
701
|
Before any provider prompt, search, source scout, or signal-discovery call, show
|
|
702
702
|
one source-plan gate and ask for approval. The plan must be visible before the
|
|
703
|
-
question, and this first approval authorizes
|
|
704
|
-
should
|
|
703
|
+
question, and this first approval only authorizes finding the best places to
|
|
704
|
+
look for buyers. It does not add anyone to the campaign yet. The gate should
|
|
705
|
+
say:
|
|
705
706
|
|
|
706
707
|
- given this campaign, the viable source options
|
|
707
708
|
- the recommended first lane
|
|
708
709
|
- why that lane fits the buyer, offer, and likely public activity
|
|
709
710
|
- what will be tested next
|
|
710
711
|
- the fallback lane if relevant posts or ICP engagement look thin
|
|
711
|
-
-
|
|
712
|
+
- what approval covers in one concise customer-facing line, such as "This only
|
|
713
|
+
approves me to look for the best places to find buyers. I won't add leads
|
|
714
|
+
yet."
|
|
712
715
|
|
|
713
716
|
Do not surface blanket source heuristics as product copy. Make the
|
|
714
717
|
recommendation specific to the campaign. If LinkedIn engagement is recommended,
|
|
715
|
-
name the exact post themes you will search
|
|
716
|
-
|
|
717
|
-
|
|
718
|
-
|
|
718
|
+
name the exact post themes you will search in plain language, such as "Power BI
|
|
719
|
+
dashboards they don't trust" or "teams trying to agree on the right KPIs."
|
|
720
|
+
Avoid using "Signal Discovery" or "source scouting" in customer-facing chat;
|
|
721
|
+
those are internal labels. If relevant public conversations look unlikely,
|
|
722
|
+
recommend the specific Sales Nav or Prospeo lane instead and say why. Do not
|
|
723
|
+
call \`search_signals\`, \`search_sales_nav\`,
|
|
719
724
|
\`search_prospeo\`,
|
|
720
725
|
\`fetch_post_engagers\`, or provider-scoped subagents until the user approves this
|
|
721
726
|
source plan or explicitly chooses a different source.
|
|
@@ -1323,7 +1328,7 @@ campaign is minted, the approved brief should carry forward the token fill
|
|
|
1323
1328
|
rules and examples: good fills, good omits, bad fills, fallback rules, and why
|
|
1324
1329
|
the bad fills are blocked.
|
|
1325
1330
|
|
|
1326
|
-
For
|
|
1331
|
+
For source decisions, confidence comes from concrete counts. Do not say
|
|
1327
1332
|
"strong sample", "73% match", or "meaningful concentration" without showing the
|
|
1328
1333
|
sample size and what was counted. Show lanes searched, timeframe, raw results,
|
|
1329
1334
|
sampled people, sampled fits as n/N (%), estimated usable people, and whether
|
package/package.json
CHANGED
|
@@ -110,10 +110,11 @@ clear business decisions, tradeoffs, and approval gates. Use product language:
|
|
|
110
110
|
Approval and safety copy should be tasteful. State what the current approval
|
|
111
111
|
covers once, in one short sentence, then move on. Do not append repeated
|
|
112
112
|
"nothing starts / no leads import / no sending" disclaimers to routine progress
|
|
113
|
-
updates. Use
|
|
114
|
-
|
|
113
|
+
updates. Use customer-facing gate language like "Next, we'll find where the
|
|
114
|
+
right buyers are already talking" or "Next gate: selected-post scrape" instead
|
|
115
|
+
of internal terms like "source scouting" or long negative lists.
|
|
115
116
|
|
|
116
|
-
When explaining
|
|
117
|
+
When explaining source decisions, show the concrete counts behind the
|
|
117
118
|
logic: lanes searched, timeframe, raw result counts, finalist posts or preview
|
|
118
119
|
rows, sampled people, sampled fits as n/N (%), estimated usable people, and the
|
|
119
120
|
confidence basis. Never show a percent like "73% match" without the numerator,
|
|
@@ -128,22 +129,27 @@ label it explicitly as not estimated from this run.
|
|
|
128
129
|
|
|
129
130
|
Before any provider prompt, search, source scout, or signal-discovery call, show
|
|
130
131
|
one source-plan gate and ask for approval. The plan must be visible before the
|
|
131
|
-
question, and this first approval authorizes
|
|
132
|
-
should
|
|
132
|
+
question, and this first approval only authorizes finding the best places to
|
|
133
|
+
look for buyers. It does not add anyone to the campaign yet. The gate should
|
|
134
|
+
say:
|
|
133
135
|
|
|
134
136
|
- given this campaign, the viable source options
|
|
135
137
|
- the recommended first lane
|
|
136
138
|
- why that lane fits the buyer, offer, and likely public activity
|
|
137
139
|
- what will be tested next
|
|
138
140
|
- the fallback lane if relevant posts or ICP engagement look thin
|
|
139
|
-
- what approval covers in one concise line
|
|
141
|
+
- what approval covers in one concise customer-facing line, such as "This only
|
|
142
|
+
approves me to look for the best places to find buyers. I won't add leads
|
|
143
|
+
yet."
|
|
140
144
|
|
|
141
145
|
Do not surface blanket source heuristics as product copy. Make the
|
|
142
146
|
recommendation specific to the campaign. If LinkedIn engagement is recommended,
|
|
143
|
-
name the exact post themes you will search
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
+
name the exact post themes you will search in plain language, such as "Power BI
|
|
148
|
+
dashboards they don't trust" or "teams trying to agree on the right KPIs."
|
|
149
|
+
Avoid using "Signal Discovery" or "source scouting" in customer-facing chat;
|
|
150
|
+
those are internal labels. If relevant public conversations look unlikely,
|
|
151
|
+
recommend the specific Sales Nav or Prospeo lane instead and say why. Do not
|
|
152
|
+
call `search_signals`, `search_sales_nav`,
|
|
147
153
|
`search_prospeo`,
|
|
148
154
|
`fetch_post_engagers`, or provider-scoped subagents until the user approves this
|
|
149
155
|
source plan or explicitly chooses a different source.
|