diff --git a/first-class-sessions.md b/first-class-sessions.md
index a035566..278c05c 100644
--- a/first-class-sessions.md
+++ b/first-class-sessions.md
@@ -7,16 +7,16 @@ Teams collaborate on agent work through the pull request today, and the
 pull request arrives too late: by the time anyone else can look, the
 intent, the conversation, and the dead ends have already evaporated,
 leaving a diff and a description of it. Collaboration does reach earlier
-than that — an agent working a chat thread already has people steering it
-together — but a thread stands apart from the changes it produces, and it
+than that: an agent working a chat thread already has people steering it
+together, but a thread stands apart from the changes it produces, and it
 fades as the channel scrolls on.
 
-The central claim is that the session is first-class: the primary
+The central claim is that the session is first-class, the primary
 component of agent-driven software work. A session is the whole unit: who
 asked for what, the conversation that steered the work, the actions agents
 and people took along the way, and the changes that came out of it. It is
 durable and addressable, at a URL that works while the work is happening
-and keeps working after. Everything else derives from the session — a pull
+and keeps working after. Everything else derives from the session. A pull
 request is one export of it, not the frame around it.
 
 ## What changes when this works
@@ -26,16 +26,15 @@ request is one export of it, not the frame around it.
   absorbs review: by the time the work is done, the people who needed to
   look already have.
 - Agent work becomes legible. A session keeps the wrong turns along with
-  the result, so a team can learn from how the work went and not only from
+  the result, so a team can learn from how the work went, not only from
   what landed.
-- Sessions feed the system's own improvement. A durable record of real
-  work — the ask, the steering, the corrections, the outcome — is an eval
-  corpus nobody had to construct: replay a past session against a new
-  agent, prompt, or policy and compare how the work goes, or mine sessions
-  for where agents stalled and where people had to step in. The same
-  record that makes work legible to the team lets the tooling study and
-  improve itself.
-- Work forks. A session is a starting point as well as a record: a new
+- Sessions feed the system's own improvement. A durable record of real work
+  is an eval corpus nobody had to construct: replay a past session against
+  a new agent, prompt, or policy and compare how the work goes, or mine
+  sessions for where agents stalled and where people had to step in. The
+  same record that makes work legible to the team lets the tooling study
+  and improve itself.
+- Work forks. A session is a starting point as well as a record. A new
   session branched off an existing one carries its context and its
   changes, so exploring an alternative does not mean starting over.
 - Sessions are context for other sessions. Anything in the ecosystem can
@@ -57,10 +56,9 @@ request is one export of it, not the frame around it.
 
 - An agent framework. Agents are built elsewhere and reason however they
   reason; the session decides what they may do.
-- A pipeline runner. Automation can open a session — a schedule, an alert,
-  a failing build — but what it opens is a session like any other, one
-  that people can join and steer. Work nobody could join is a different
-  tool.
+- A pipeline runner. A schedule, an alert, or a failing build can open a
+  session, but what opens is a session like any other, one that people can
+  join and steer. Work nobody could join is a different tool.
 - A hosted product. It runs where the team runs, inside the team's own
   trust boundary.